😶‍🌫️ OTL

‌ ‍ ‎ ‏ ‌ ‍

Maani

·

AI & ML interests

Novel Architectures | System Design

Recent Activity

liked a model 1 day ago

Qwen/Qwen-Image-2.1

upvoted a collection 1 day ago

THE BEST CODER 2026

reacted to Datdanboi25's post with 🔥 1 day ago

THE SLM FRONTIER ADVANCES! https://huggingface.co/bench-labs/cagliostro-v3 just hit an Intelligence Index of 26.13 on the https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard a 146M-param model trained completely from scratch on a single consumer GPU. That's 2nd place overall, and as far as I can tell, the most capable SLM trained on consumer hardware to date. Beating SmolLM-135m on 1/8th of the data is just silly levels of efficiency. Big congrats to the @BenchLabs team and specifically @TobiasLogic !

View all activity

Organizations

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf 1 day ago

It is fighting with the harness, chat template and blaming the human operator

#35 opened 3 days ago by

New activity in prism-ml/Ternary-Bonsai-27B-gguf 19 days ago

Benchmark: 27B Q2_0 vs Qwen3.6-27B IQ2_XXS on one RTX 5060 Ti 16 GB (quality@budget, speed, VRAM, energy)

#58 opened 24 days ago by

New activity in OBLITERATUS/Qwen3.8-27B-OBLITERATED 26 days ago

meth bench failed (partially)

#11 opened 26 days ago by

New activity in prism-ml/Ternary-Bonsai-27B-gguf about 1 month ago

Will the qwen3.8-27b version be produced?

#54 opened about 1 month ago by

New activity in LiquidAI/LFM2.5-2.6B about 1 month ago

Speculative Decoding

#6 opened about 2 months ago by

New activity in DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF about 2 months ago

uncensored?

#15 opened about 2 months ago by

New activity in prism-ml/Ternary-Bonsai-27B-gguf about 2 months ago

Appreciation Post

#47 opened 2 months ago by

New activity in prism-ml/Ternary-Bonsai-27B-gguf 2 months ago

loopy, hallucinates and tool calling problems

#41 opened 2 months ago by

Very promising model

#46 opened 2 months ago by

New activity in google/gemma-4-E2B-it 3 months ago

Appreciation Post

#37 opened 3 months ago by

New activity in allura-forge/Llama-3.3-8B-Instruct 8 months ago

This model is broken.

#4 opened 9 months ago by

New activity in EssentialAI/rnj-1-instruct 9 months ago

gemma3 is absolutely trash.

#9 opened 9 months ago by

New activity in EssentialAI/rnj-1-instruct 10 months ago

After a long time, finally a capable little coder!

#2 opened 10 months ago by

New activity in Maani/PXZNNO 11 months ago

It seems the README is wrong

#1 opened 11 months ago by

New activity in dphn/Dolphin-X1-8B 11 months ago

not uncensored.

#1 opened 11 months ago by

New activity in LiquidAI/LFM2-2.6B 12 months ago

Exceptional

#3 opened 12 months ago by

is this reasoning model?

#1 opened 12 months ago by

New activity in google/vaultgemma-1b about 1 year ago

big kudos and congrats

#3 opened about 1 year ago by

New activity in xai-org/grok-2 about 1 year ago

excuse me

#36 opened about 1 year ago by

EXTREMELY BASED

#3 opened about 1 year ago by