Writing Down the Line Between Luck and Skill
โข 12
AI & ML interests
Contact: arxivgpt@gmail.com
Recent Activity
View all activity
Papers
View all Papers Articles
SeaWolf-AIย
updated a
Space about 7 hours ago
SeaWolf-AIย
updated a
Space about 9 hours ago
SeaWolf-AIย
posted an update 1 day ago
Post
1928
Can AI beat the market? Nobody has actually measured it.
We opened a 122-day public experiment to find out. $2,000 in prizes.
Here is the problem with every trading result you have ever read. Someone returns 30% in a month. Skill or luck? There has never been a way to tell, because nobody measured how far a player with zero skill could have gone over the same window.
So we measured it first. Twenty thousand random players, per asset, charged the same fees.
Bitcoin +86.6%. NVIDIA +51.7%. Crude oil +26.9%. Gold +9.2%.
That is the luck ceiling. A return below it is not evidence of skill, and every row on our leaderboard shows where it sits against that line.
How you compete: submit one number between โ1.0 and +1.0. It holds until you replace it, traded against live prices with real execution costs. Leverage is fixed at 1, so betting bigger is not a way to win. The answer lives in the future โ the world writes it after you submit, which means fitting the past cannot help you.
Humans move a slider. Agents attach an MCP server and gain four tools, then you tell them "enter the challenge."
We already found something before the season began. Thirteen well-known rules, run from 1 January through the same scorer: Stochastic 14/3 finishes 1st on NVIDIA at +43% and 12th on Bitcoin at โ25%. Donchian breakout does the exact opposite โ last on NVIDIA, first on Bitcoin. The ranking inverts. "Which indicator is good" turns out not to be a well-posed question; the character of the market decides.
Four assets: NVIDIA, Bitcoin, Gold, Crude Oil. $500 to the top return in each. 24 August to 24 December 2026.
The organisers do not compete. Three baselines โ buy and hold, volatility targeting, random โ sit in the same table instead, because a leaderboard without a scale cannot be read.
The scoring code is public. Read what it does before you enter.
FINAL-Bench/finchal
https://huggingface.co/blog/FINAL-Bench/financial-forecast-challenge
We opened a 122-day public experiment to find out. $2,000 in prizes.
Here is the problem with every trading result you have ever read. Someone returns 30% in a month. Skill or luck? There has never been a way to tell, because nobody measured how far a player with zero skill could have gone over the same window.
So we measured it first. Twenty thousand random players, per asset, charged the same fees.
Bitcoin +86.6%. NVIDIA +51.7%. Crude oil +26.9%. Gold +9.2%.
That is the luck ceiling. A return below it is not evidence of skill, and every row on our leaderboard shows where it sits against that line.
How you compete: submit one number between โ1.0 and +1.0. It holds until you replace it, traded against live prices with real execution costs. Leverage is fixed at 1, so betting bigger is not a way to win. The answer lives in the future โ the world writes it after you submit, which means fitting the past cannot help you.
Humans move a slider. Agents attach an MCP server and gain four tools, then you tell them "enter the challenge."
We already found something before the season began. Thirteen well-known rules, run from 1 January through the same scorer: Stochastic 14/3 finishes 1st on NVIDIA at +43% and 12th on Bitcoin at โ25%. Donchian breakout does the exact opposite โ last on NVIDIA, first on Bitcoin. The ranking inverts. "Which indicator is good" turns out not to be a well-posed question; the character of the market decides.
Four assets: NVIDIA, Bitcoin, Gold, Crude Oil. $500 to the top return in each. 24 August to 24 December 2026.
The organisers do not compete. Three baselines โ buy and hold, volatility targeting, random โ sit in the same table instead, because a leaderboard without a scale cannot be read.
The scoring code is public. Read what it does before you enter.
FINAL-Bench/finchal
https://huggingface.co/blog/FINAL-Bench/financial-forecast-challenge
- 7 replies
SeaWolf-AIย
published an article 1 day ago
Article
Writing Down the Line Between Luck and Skill
FINAL-Bench
โข โข 12 SeaWolf-AIย
updated a
Space 1 day ago
SeaWolf-AIย
published a
Space 1 day ago
SeaWolf-AIย
posted an update 3 days ago
Post
3695
We opened a benchmark for drug property prediction tools. LEADBOARD: 21 boards across 7 disciplines, 18,382 held-out compounds, labels we never hand out.
Two numbers we hit while building it are the reason it exists.
First. Split the hERG cardiotoxicity data at random and you get AUROC 0.818. Split it by first-report year instead and you get 0.606. Same molecules, same fingerprints, same learner, same hyperparameters. The only thing that changed was where the line went, and the score moved 0.211. That is a wider gap than you will find between most competing methods in the literature.
Second. On 7 of our 19 regression boards, predicting the training mean for everything has a lower MAE than a trained gradient-boosted model. hERG is one of them, 0.599 against 0.589. The trained model loses.
So every board publishes its homework before anyone submits. Three untrained baselines, the measured experimental noise floor from compounds that appear in two or more papers, and exactly how the test set was cut. A gap smaller than the noise floor is not a difference in skill, and you should be able to see that without guessing.
Entering is simple. Download a test set that contains structures and nothing else, predict with whatever you like, upload a two-column CSV of compound_id and prediction. Trained model, physics engine, LLM, rule of thumb. We do not care what is inside. We measure the output.
Post: https://huggingface.co/blog/FINAL-Bench/leadboard-drug
Leaderboard: FINAL-Bench/leadboard
Two numbers we hit while building it are the reason it exists.
First. Split the hERG cardiotoxicity data at random and you get AUROC 0.818. Split it by first-report year instead and you get 0.606. Same molecules, same fingerprints, same learner, same hyperparameters. The only thing that changed was where the line went, and the score moved 0.211. That is a wider gap than you will find between most competing methods in the literature.
Second. On 7 of our 19 regression boards, predicting the training mean for everything has a lower MAE than a trained gradient-boosted model. hERG is one of them, 0.599 against 0.589. The trained model loses.
So every board publishes its homework before anyone submits. Three untrained baselines, the measured experimental noise floor from compounds that appear in two or more papers, and exactly how the test set was cut. A gap smaller than the noise floor is not a difference in skill, and you should be able to see that without guessing.
Entering is simple. Download a test set that contains structures and nothing else, predict with whatever you like, upload a two-column CSV of compound_id and prediction. Trained model, physics engine, LLM, rule of thumb. We do not care what is inside. We measure the output.
Post: https://huggingface.co/blog/FINAL-Bench/leadboard-drug
Leaderboard: FINAL-Bench/leadboard
- 6 replies
SeaWolf-AIย
published an article 3 days ago
Article
We changed one line and the benchmark score moved 0.21 AUROC
FINAL-Bench
โข โข 10 SeaWolf-AIย
published a
Space 3 days ago
SeaWolf-AIย
updated a
Space 3 days ago
SeaWolf-AIย
posted an update 4 days ago
Post
4032
๐ Open Materials Challenge, Season 1 โ Solid-State Battery Electrolytes
A solid-state battery replaces the liquid electrolyte of a lithium-ion cell with a solid. It does not catch fire, it lasts longer, and it can hold more. What has not been solved is finding a material that is solid and still lets lithium through.
Such a material has to do four things at once: give lithium a path to move along, block electrons, hold up at the charging voltage, and survive contact with the lithium-metal anode without decomposing. Plenty of materials manage three. Very few manage all four.
This challenge looks for candidates, together. You submit one composition โ for example Li3YCl6. We score it computationally and place it on the board. There is no prize.
Scoring (100 points)
Oxidation stability 40 does it resist decomposing as the voltage rises
Lithium-metal stability 35 does it survive contact with the anode
Use novelty 25 higher if it has not been reported as an electrolyte
Entry condition a percolating path for lithium must exist
Ionic conductivity is not a scored axis this season. Every value is a computational estimate and implies nothing about real performance or safety.
The board also carries seven electrolytes in actual use โ LGPS, argyrodite, LLZO, LATP and others. They are scored but hold no rank. They are there so you can see where materials people already build with happen to land.
Compositions are private by default. Nothing is disclosed unless you choose to publish it, and each entry is recorded with its timestamp. If a third party asks to discuss a particular entry, we pass the request along โ never the submitter's identity, unless they agree to it.
Season 1 runs 2026-08-21 to 11-30. A participation guide and a set of prompts are included.
๐ FINAL-Bench/open-materials-challenge
Our sister challenge๐งชhttps://huggingface.co/spaces/FINAL-Bench/open-discovery-challenge
A solid-state battery replaces the liquid electrolyte of a lithium-ion cell with a solid. It does not catch fire, it lasts longer, and it can hold more. What has not been solved is finding a material that is solid and still lets lithium through.
Such a material has to do four things at once: give lithium a path to move along, block electrons, hold up at the charging voltage, and survive contact with the lithium-metal anode without decomposing. Plenty of materials manage three. Very few manage all four.
This challenge looks for candidates, together. You submit one composition โ for example Li3YCl6. We score it computationally and place it on the board. There is no prize.
Scoring (100 points)
Oxidation stability 40 does it resist decomposing as the voltage rises
Lithium-metal stability 35 does it survive contact with the anode
Use novelty 25 higher if it has not been reported as an electrolyte
Entry condition a percolating path for lithium must exist
Ionic conductivity is not a scored axis this season. Every value is a computational estimate and implies nothing about real performance or safety.
The board also carries seven electrolytes in actual use โ LGPS, argyrodite, LLZO, LATP and others. They are scored but hold no rank. They are there so you can see where materials people already build with happen to land.
Compositions are private by default. Nothing is disclosed unless you choose to publish it, and each entry is recorded with its timestamp. If a third party asks to discuss a particular entry, we pass the request along โ never the submitter's identity, unless they agree to it.
Season 1 runs 2026-08-21 to 11-30. A participation guide and a set of prompts are included.
๐ FINAL-Bench/open-materials-challenge
Our sister challenge๐งชhttps://huggingface.co/spaces/FINAL-Bench/open-discovery-challenge
SeaWolf-AIย
published a
Space 4 days ago
SeaWolf-AIย
posted an update 6 days ago
Post
3963
3,631 candidate molecules arrived in five days, from 83 accounts โ roughly 700 a day. Far more than we expected. Thank you.
Yesterday we opened the third season and 224 arrived within a day: Chagas disease.
Why this disease
Around 6 million people live with it, mostly in Latin America (WHO). Many carry it for decades without knowing, while the heart is slowly damaged. There are two drugs and both date from the 1960s, hard enough to tolerate that many patients cannot finish the two-month course.
Sixty years without a new drug is not only a scientific problem. Most patients live where development costs cannot be recovered, which is why WHO calls this a neglected tropical disease.
But the cost of proposing a candidate and filtering it has changed. So it seemed worth asking whether work nobody funds could be done by many people sharing it out.
The problem this season
The target is CYP51, the enzyme T. cruzi uses to build its membrane sterols. Block it and the parasite cannot survive. The difficulty is that we carry the same enzyme.
Scoring: binding 30 ยท selectivity 30 ยท ADMET 15 ยท whole-cell 10 ยท novelty 10 ยท synthesis 5
Selectivity carries 30 points because nobody has solved it. Among the approved azoles on the board as reference compounds, some score 0 on selectivity โ not a scorer fault, but the measurement.
Taking part
Design with any model, submit a SMILES, scored within minutes. Five ready-to-paste prompts per season, and the full rubric is published. Your molecule stays yours; private submission is the default.
Prizes โ 4,000 USD across three seasons
Malaria 30 Sep ยท 1,000 | Tuberculosis 31 Oct ยท 2,000 | Chagas 30 Nov ยท 1,000
We know this does not cover the time you spend. It is a way of saying the work had worth.
FINAL-Bench/open-discovery-challenge
Yesterday we opened the third season and 224 arrived within a day: Chagas disease.
Why this disease
Around 6 million people live with it, mostly in Latin America (WHO). Many carry it for decades without knowing, while the heart is slowly damaged. There are two drugs and both date from the 1960s, hard enough to tolerate that many patients cannot finish the two-month course.
Sixty years without a new drug is not only a scientific problem. Most patients live where development costs cannot be recovered, which is why WHO calls this a neglected tropical disease.
But the cost of proposing a candidate and filtering it has changed. So it seemed worth asking whether work nobody funds could be done by many people sharing it out.
The problem this season
The target is CYP51, the enzyme T. cruzi uses to build its membrane sterols. Block it and the parasite cannot survive. The difficulty is that we carry the same enzyme.
Scoring: binding 30 ยท selectivity 30 ยท ADMET 15 ยท whole-cell 10 ยท novelty 10 ยท synthesis 5
Selectivity carries 30 points because nobody has solved it. Among the approved azoles on the board as reference compounds, some score 0 on selectivity โ not a scorer fault, but the measurement.
Taking part
Design with any model, submit a SMILES, scored within minutes. Five ready-to-paste prompts per season, and the full rubric is published. Your molecule stays yours; private submission is the default.
Prizes โ 4,000 USD across three seasons
Malaria 30 Sep ยท 1,000 | Tuberculosis 31 Oct ยท 2,000 | Chagas 30 Nov ยท 1,000
We know this does not cover the time you spend. It is a way of saying the work had worth.
FINAL-Bench/open-discovery-challenge
SeaWolf-AIย
updated a
collection 9 days ago
SeaWolf-AIย
posted an update 10 days ago
Post
4277
๐งฌ Your AI can design a malaria drug candidate. Can it tell you whether it's any good?
Open Discovery Challenge #1 โ Malaria is live. Design a molecule with any model โ OpenAI, Claude, Gemini, Qwen, KIMI, DeepSeek, open weights, or by hand โ submit it as SMILES, and it's scored in minutes on whole-cell activity, target binding, selectivity over the human enzyme, ADMET, novelty and synthesisability.
You can check the scoring instead of trusting it. Approved drugs sit on the same leaderboard as the entries: DSM265, a clinical-stage antimalarial, scores 50.9. Teriflunomide โ approved, but it hits the human enzyme โ scores 2.8. Caffeine scores 1.8. If the clinical candidate lands on top and coffee lands at the bottom, the scorer discriminates.
We caught 14 defects before opening โ conventional toxicity cutoffs rejected all three approved antimalarials and coffee. All written up, along with the rule we now hold everything to: a gate that rejects an approved drug is a broken gate.
Your molecule stays yours. No patent interest, nothing into our pipeline. You choose whether it's published โ and publishing can cost you patentability, so we say so.
USD 1,000 to the top entry when Season #1 closes 30 September 2026 โ not payment for your tokens, but a way of saying the work had worth.
Malaria killed ~597,000 people in 2023, three quarters of them children under five. Not for want of chemistry โ for want of a market.
No chemistry needed: the guide ships five prompts you can paste straight into your model, and the full rubric is published.
๐ https://huggingface.co/blog/FINAL-Bench/open-discovery-challenge
๐ FINAL-Bench/open-discovery-challenge
Computational assessments of candidates โ not measurements, not claims of efficacy.
Open Discovery Challenge #1 โ Malaria is live. Design a molecule with any model โ OpenAI, Claude, Gemini, Qwen, KIMI, DeepSeek, open weights, or by hand โ submit it as SMILES, and it's scored in minutes on whole-cell activity, target binding, selectivity over the human enzyme, ADMET, novelty and synthesisability.
You can check the scoring instead of trusting it. Approved drugs sit on the same leaderboard as the entries: DSM265, a clinical-stage antimalarial, scores 50.9. Teriflunomide โ approved, but it hits the human enzyme โ scores 2.8. Caffeine scores 1.8. If the clinical candidate lands on top and coffee lands at the bottom, the scorer discriminates.
We caught 14 defects before opening โ conventional toxicity cutoffs rejected all three approved antimalarials and coffee. All written up, along with the rule we now hold everything to: a gate that rejects an approved drug is a broken gate.
Your molecule stays yours. No patent interest, nothing into our pipeline. You choose whether it's published โ and publishing can cost you patentability, so we say so.
USD 1,000 to the top entry when Season #1 closes 30 September 2026 โ not payment for your tokens, but a way of saying the work had worth.
Malaria killed ~597,000 people in 2023, three quarters of them children under five. Not for want of chemistry โ for want of a market.
No chemistry needed: the guide ships five prompts you can paste straight into your model, and the full rubric is published.
๐ https://huggingface.co/blog/FINAL-Bench/open-discovery-challenge
๐ FINAL-Bench/open-discovery-challenge
Computational assessments of candidates โ not measurements, not claims of efficacy.
- 12 replies
SeaWolf-AIย
posted an update 11 days ago
Post
3298
AX-Ray: Safety Diagnostics for AI/AX Models
AI models can no longer be evaluated only by capability scores. As models move into public services, enterprise workflows, scientific research, and administrative decision support, we need a second layer of evaluation: whether the model behaves safely, structurally, and consistently under real deployment conditions.
VIDRAFT AX-Ray is a public AI/AX safety diagnostic initiative powered by FINAL-Bench Diagnostics. AX-Ray evaluates models across a structured guideline framework, including model-level safety, AX deployment readiness, and agent/service operation risks. The public diagnostic catalog contains 117 diagnostic items, mapped to legal, regulatory, ethical, and religious-law governance contexts so that safety review can be discussed in a form closer to real institutional responsibility.
A central finding of AX-Ray is causal leakage: a structural defect where information that should not influence an earlier reasoning state appears to affect model behavior. AX-Ray presents a public case of diagnosing, reproducing, and demonstrating causal leakage in two general-purpose public models. This matters because such defects are not exposed by ordinary benchmark scores. A model can appear capable while still carrying hidden safety or integrity risks.
Explore the live leaderboard, diagnostic reports, and public dataset here:
- AX-Ray Space: FINAL-Bench/AX-RAY
- AX-Ray Dataset: FINAL-Bench/AX-RAY
- Technical Article: https://huggingface.co/blog/FINAL-Bench/ax-ray
AX-Ray is intended as a practical guideline for moving AI evaluation beyond โhow smart is the model?โ toward โcan this model be trusted, governed, and deployed safely?โ
AI models can no longer be evaluated only by capability scores. As models move into public services, enterprise workflows, scientific research, and administrative decision support, we need a second layer of evaluation: whether the model behaves safely, structurally, and consistently under real deployment conditions.
VIDRAFT AX-Ray is a public AI/AX safety diagnostic initiative powered by FINAL-Bench Diagnostics. AX-Ray evaluates models across a structured guideline framework, including model-level safety, AX deployment readiness, and agent/service operation risks. The public diagnostic catalog contains 117 diagnostic items, mapped to legal, regulatory, ethical, and religious-law governance contexts so that safety review can be discussed in a form closer to real institutional responsibility.
A central finding of AX-Ray is causal leakage: a structural defect where information that should not influence an earlier reasoning state appears to affect model behavior. AX-Ray presents a public case of diagnosing, reproducing, and demonstrating causal leakage in two general-purpose public models. This matters because such defects are not exposed by ordinary benchmark scores. A model can appear capable while still carrying hidden safety or integrity risks.
Explore the live leaderboard, diagnostic reports, and public dataset here:
- AX-Ray Space: FINAL-Bench/AX-RAY
- AX-Ray Dataset: FINAL-Bench/AX-RAY
- Technical Article: https://huggingface.co/blog/FINAL-Bench/ax-ray
AX-Ray is intended as a practical guideline for moving AI evaluation beyond โhow smart is the model?โ toward โcan this model be trusted, governed, and deployed safely?โ
- 2 replies
SeaWolf-AIย
posted an update 22 days ago
Post
3437
We wrote up our run in The Fast Gemma Challenge โ as vidraft-darwin โ and wanted to share the recipe. ๐
gemma-challenge/gemma-dashboard
Verified result: 510.58 TPS at PPL 2.3930 on a single A10G (fw188-ctk49-n64-patchbridge, re-run & VERIFIED). Honest note: on raw TPS there are faster runs (535+), but those went over the PPL bar and didn't verify โ what we're proud of is the fastest result that keeps quality.
The recipe is already open, so we explained each piece: sliding-window W188, CTK49 kernel tuning, noprecache (honest, verifiable measurement), and an N64 synthetic warmup bridge that shrinks the publicโprivate gap (~15 TPS), plus INT4 + MTP K=7 + CUDA-graph capture. One rule: only stack quality-neutral speedups.
Huge thanks to @firfir-cast , @gemma-slayer , @chiku-inu , @kenyan-duma , @dixie-flatline and everyone who shared their experiments. Full write-up
๐
https://huggingface.co/blog/FINAL-Bench/fast-gemma
gemma-challenge/gemma-dashboard
Verified result: 510.58 TPS at PPL 2.3930 on a single A10G (fw188-ctk49-n64-patchbridge, re-run & VERIFIED). Honest note: on raw TPS there are faster runs (535+), but those went over the PPL bar and didn't verify โ what we're proud of is the fastest result that keeps quality.
The recipe is already open, so we explained each piece: sliding-window W188, CTK49 kernel tuning, noprecache (honest, verifiable measurement), and an N64 synthetic warmup bridge that shrinks the publicโprivate gap (~15 TPS), plus INT4 + MTP K=7 + CUDA-graph capture. One rule: only stack quality-neutral speedups.
Huge thanks to @firfir-cast , @gemma-slayer , @chiku-inu , @kenyan-duma , @dixie-flatline and everyone who shared their experiments. Full write-up
๐
https://huggingface.co/blog/FINAL-Bench/fast-gemma
- 8 replies
SeaWolf-AIย
posted an update about 1 month ago
Post
6379
๐ผ๏ธ POCKET-Image โ the POCKET series goes visual: character-perfect text in any language, on-device
A new model in VIDRAFT's POCKET family. POCKET put 35B-class models on phones and no-GPU PCs. POCKET-Image carries the same "big capability, small hardware" idea into image generation โ and fixes the one thing nearly every image model gets wrong: text.
Type "์๋ ํ์ธ์" into a typical model and you get "์ใ ๊ธฐ." Hangul alone composes 11,172 syllable blocks; Arabic connects its letters; Thai stacks marks. Diffusion models draw scripts as shapes, so they smear. POCKET-Image renders every glyph exactly โ ํ๊ตญ์ด ยท ไธญๆ ยท ๆฅๆฌ่ช ยท ุงูุนุฑุจูุฉ (RTL) ยท เนเธเธข ยท Latin and more โ onto any scene you describe.
What it is:
โข 100% accurate text, any language โ where global models produce gibberish
โข Any background from a prompt โ text is optional (empty โ a pure image)
โข No GPU, no NPU โ runs on plain CPU + RAM via the POCKET-Core engine
โข Measured footprint: 8.6 GB (RTX 3050/4060) ยท 4.5 GB (offloaded, 6 GB cards) ยท 13.4 GB (MacBook, 16 GB+)
โข Windows ยท macOS ยท Linux ยท fully local, no cloud
Built on the open, commercial-friendly Z-Image (Apache-2.0) foundation.
Honest note: the text is the guaranteed-correct part โ the surrounding scene is ordinary generation, so a busy foreground can crowd the letters. We say so; clean backgrounds stay razor-sharp.
๐จ Studio โ generate right here, any language:
FINAL-Bench/POCKET-Image-Studio
๐งฉ Model card:
FINAL-Bench/POCKET-Image-Zimage
๐ The POCKET collection:
https://huggingface.co/collections/FINAL-Bench/pocket-models
A new model in VIDRAFT's POCKET family. POCKET put 35B-class models on phones and no-GPU PCs. POCKET-Image carries the same "big capability, small hardware" idea into image generation โ and fixes the one thing nearly every image model gets wrong: text.
Type "์๋ ํ์ธ์" into a typical model and you get "์ใ ๊ธฐ." Hangul alone composes 11,172 syllable blocks; Arabic connects its letters; Thai stacks marks. Diffusion models draw scripts as shapes, so they smear. POCKET-Image renders every glyph exactly โ ํ๊ตญ์ด ยท ไธญๆ ยท ๆฅๆฌ่ช ยท ุงูุนุฑุจูุฉ (RTL) ยท เนเธเธข ยท Latin and more โ onto any scene you describe.
What it is:
โข 100% accurate text, any language โ where global models produce gibberish
โข Any background from a prompt โ text is optional (empty โ a pure image)
โข No GPU, no NPU โ runs on plain CPU + RAM via the POCKET-Core engine
โข Measured footprint: 8.6 GB (RTX 3050/4060) ยท 4.5 GB (offloaded, 6 GB cards) ยท 13.4 GB (MacBook, 16 GB+)
โข Windows ยท macOS ยท Linux ยท fully local, no cloud
Built on the open, commercial-friendly Z-Image (Apache-2.0) foundation.
Honest note: the text is the guaranteed-correct part โ the surrounding scene is ordinary generation, so a busy foreground can crowd the letters. We say so; clean backgrounds stay razor-sharp.
๐จ Studio โ generate right here, any language:
FINAL-Bench/POCKET-Image-Studio
๐งฉ Model card:
FINAL-Bench/POCKET-Image-Zimage
๐ The POCKET collection:
https://huggingface.co/collections/FINAL-Bench/pocket-models
SeaWolf-AIย
posted an update about 1 month ago
Post
3135
POCKET now speaks Gemma 4 โ a 26B model that loads in every app, and runs on your PC with no GPU
We're adding a Gemma-4 sibling to POCKET: POCKET-26B, built from Google's Gemma-4-26B-A4B (Apache-2.0). Our flagship POCKET-35B is a Qwen-family MoE and needs a recent llama.cpp; POCKET-26B trades a little size for the thing people kept asking for โ it just loads, everywhere, today: Ollama, LM Studio, PocketPal, MLX, any stock llama.cpp. No fork, no bleeding-edge runtime, no CUDA, no cloud.
It's a sparse Mixture-of-Experts (25.2B total, ~4B active per token), so the work per token stays small โ a real 26B that generates on a CPU with no graphics card.
Two things make it stand out:
1) Universal compatibility. Gemma 4 is a standard, widely-supported architecture, so POCKET-26B runs on the tools you already have โ no waiting for your app to add a new model type.
2) Quality that survives compression. Measured GPQA-Diamond (198 q, greedy):
โข Full base: 67.7%
โข POCKET-26B Q4_K_M (17 GB): 67.7% โ lossless
โข POCKET-26B Q2_K (11 GB): 67.2% โ near-lossless, at 11 GB
Live, on a CPU-only box (our demo Space โ POCKET-26B vs Bonsai-27B, same machine, same stock llama.cpp): POCKET-26B โ 19 tok/s vs Bonsai โ 6 tok/s โ about 3ร faster generation, no GPU. (Honest notes: shared CPU box, sequential race; a dedicated machine is faster.)
Where it fits in the family:
โข POCKET-35B (Qwen MoE) โ bigger, top-tier, needs a recent llama.cpp.
โข POCKET-26B (Gemma 4) โ loads in any app, quality-robust when compressed. The demo runs the Q4_K_M build; Q2_K (11 GB) is the smallest footprint. For a true โค8 GB phone, the 5 GB POCKET-KR (Qwen) is still the pick.
Try it and grab it:
๐ฅ๏ธ Live demo (Gemma4-based, answering on a CPU, no GPU): FINAL-Bench/POCKET-26B-CPU
๐ฆ POCKET-26B-GGUF (Q4_K_M 17 GB ยท Q2_K 11 GB): FINAL-Bench/POCKET-26B-GGUF
๐ POCKET collection: https://huggingface.co/collections/FINAL-Bench/pocket-models
We're adding a Gemma-4 sibling to POCKET: POCKET-26B, built from Google's Gemma-4-26B-A4B (Apache-2.0). Our flagship POCKET-35B is a Qwen-family MoE and needs a recent llama.cpp; POCKET-26B trades a little size for the thing people kept asking for โ it just loads, everywhere, today: Ollama, LM Studio, PocketPal, MLX, any stock llama.cpp. No fork, no bleeding-edge runtime, no CUDA, no cloud.
It's a sparse Mixture-of-Experts (25.2B total, ~4B active per token), so the work per token stays small โ a real 26B that generates on a CPU with no graphics card.
Two things make it stand out:
1) Universal compatibility. Gemma 4 is a standard, widely-supported architecture, so POCKET-26B runs on the tools you already have โ no waiting for your app to add a new model type.
2) Quality that survives compression. Measured GPQA-Diamond (198 q, greedy):
โข Full base: 67.7%
โข POCKET-26B Q4_K_M (17 GB): 67.7% โ lossless
โข POCKET-26B Q2_K (11 GB): 67.2% โ near-lossless, at 11 GB
Live, on a CPU-only box (our demo Space โ POCKET-26B vs Bonsai-27B, same machine, same stock llama.cpp): POCKET-26B โ 19 tok/s vs Bonsai โ 6 tok/s โ about 3ร faster generation, no GPU. (Honest notes: shared CPU box, sequential race; a dedicated machine is faster.)
Where it fits in the family:
โข POCKET-35B (Qwen MoE) โ bigger, top-tier, needs a recent llama.cpp.
โข POCKET-26B (Gemma 4) โ loads in any app, quality-robust when compressed. The demo runs the Q4_K_M build; Q2_K (11 GB) is the smallest footprint. For a true โค8 GB phone, the 5 GB POCKET-KR (Qwen) is still the pick.
Try it and grab it:
๐ฅ๏ธ Live demo (Gemma4-based, answering on a CPU, no GPU): FINAL-Bench/POCKET-26B-CPU
๐ฆ POCKET-26B-GGUF (Q4_K_M 17 GB ยท Q2_K 11 GB): FINAL-Bench/POCKET-26B-GGUF
๐ POCKET collection: https://huggingface.co/collections/FINAL-Bench/pocket-models
- 3 replies
SeaWolf-AIย
posted an update about 1 month ago
Post
4064
๐ฑ POCKET โ a 35-billion-parameter model that runs on your iPhone, and on your PC with no GPU
We're releasing POCKET, VIDRAFT's flagship Darwin-36B-Opus compressed for on-device use. No fork, no CUDA, no cloud โ it runs on stock llama.cpp. It's a sparse Mixture-of-Experts model (256 experts, only 8 active per token), so the file can be large while the work per token stays small. That's what lets a 35B model run on a phone, and generate fast on a CPU with no graphics card.
Measured (POCKET-35B IQ1_M vs Bonsai-27B Q1_0):
โข CPU generate (Xeon, 16 threads): 27.0 vs 10.1 tok/s โ 2.69ร faster
โข GPU generate (H100): 197 vs 89 tok/s โ 2.22ร faster
โข GPU prompt processing (H100): 753 vs 1816 โ 0.41ร (Bonsai wins this one โ MoE prefill wakes every expert, so sparsity stops helping there. We say so.)
โข Quality (HellaSwag, 400 q): 61.0% vs 60.0% โ a tie (confidence intervals overlap)
On a real consumer laptop โ MacBook M3 Pro (18 GB) โ POCKET wins every axis, prompt processing included:
โข Metal generate: 25.4 vs 12.8 โ 1.99ร
โข CPU generate: 13.8 vs 4.4 โ 3.13ร
โข Metal prompt: 240.7 vs 73.4 โ 3.28ร
One more quiet fact: the same-size, quality-oriented rival Ternary-Bonsai-27B (7.2 GB) fails to load in upstream llama.cpp at all โ it needs the PrismML fork. POCKET runs on the tools you already have: LM Studio, Ollama, PocketPal, MLX.
๐ Full story (tech, measurements, recipes): https://huggingface.co/blog/FINAL-Bench/pocket
Models:
๐ฆ POCKET-35B-GGUF (PC / server, no GPU): FINAL-Bench/POCKET-35B-GGUF
๐ฐ๐ท POCKET-KR-GGUF (Android): FINAL-Bench/POCKET-KR-GGUF
๐ POCKET-KR-MLX (iPhone / Mac): FINAL-Bench/POCKET-KR-MLX
๐ POCKET-EN-GGUF (English phone / PC): FINAL-Bench/POCKET-EN-GGUF
๐ฅ๏ธ Live demo (answering on a CPU, no GPU): FINAL-Bench/POCKET-35B-CPU
๐ Collection: FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6
We're releasing POCKET, VIDRAFT's flagship Darwin-36B-Opus compressed for on-device use. No fork, no CUDA, no cloud โ it runs on stock llama.cpp. It's a sparse Mixture-of-Experts model (256 experts, only 8 active per token), so the file can be large while the work per token stays small. That's what lets a 35B model run on a phone, and generate fast on a CPU with no graphics card.
Measured (POCKET-35B IQ1_M vs Bonsai-27B Q1_0):
โข CPU generate (Xeon, 16 threads): 27.0 vs 10.1 tok/s โ 2.69ร faster
โข GPU generate (H100): 197 vs 89 tok/s โ 2.22ร faster
โข GPU prompt processing (H100): 753 vs 1816 โ 0.41ร (Bonsai wins this one โ MoE prefill wakes every expert, so sparsity stops helping there. We say so.)
โข Quality (HellaSwag, 400 q): 61.0% vs 60.0% โ a tie (confidence intervals overlap)
On a real consumer laptop โ MacBook M3 Pro (18 GB) โ POCKET wins every axis, prompt processing included:
โข Metal generate: 25.4 vs 12.8 โ 1.99ร
โข CPU generate: 13.8 vs 4.4 โ 3.13ร
โข Metal prompt: 240.7 vs 73.4 โ 3.28ร
One more quiet fact: the same-size, quality-oriented rival Ternary-Bonsai-27B (7.2 GB) fails to load in upstream llama.cpp at all โ it needs the PrismML fork. POCKET runs on the tools you already have: LM Studio, Ollama, PocketPal, MLX.
๐ Full story (tech, measurements, recipes): https://huggingface.co/blog/FINAL-Bench/pocket
Models:
๐ฆ POCKET-35B-GGUF (PC / server, no GPU): FINAL-Bench/POCKET-35B-GGUF
๐ฐ๐ท POCKET-KR-GGUF (Android): FINAL-Bench/POCKET-KR-GGUF
๐ POCKET-KR-MLX (iPhone / Mac): FINAL-Bench/POCKET-KR-MLX
๐ POCKET-EN-GGUF (English phone / PC): FINAL-Bench/POCKET-EN-GGUF
๐ฅ๏ธ Live demo (answering on a CPU, no GPU): FINAL-Bench/POCKET-35B-CPU
๐ Collection: FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6
- 5 replies