bytkim/Qwen3.8-27B-pi-GGUF
Text Generation • 27B • Updated • 2.83k • 16
Alex Hant
hardhant
AI & ML interests
None yet
Recent Activity
liked a model about 22 hours ago
bytkim/Qwen3.8-27B-pi-GGUF liked a model 1 day ago
CohereLabs/North-Small-Translate-1.0-w4a16 liked a model 2 days ago
FINAL-Bench/Darwin-180B-RSIOrganizations
None yet
liked a
model about 22 hours ago
liked a
model 1 day ago
liked a
model 2 days ago
reacted to SeaWolf-AI's post with 👍 3 days ago
Post
6090
🧬 Darwin-180B-RSI — an AI that learns from itself and knows when it's right
👉 FINAL-Bench/Darwin-180B-RSI
🧬 Darwin — crossbreed and evolve the parent
Darwin diagnoses strong parent models like an MRI, inherits only their best parts, and evolves the weak spots — producing a child stronger than its parents.
Father model: Qwen3.8-Flash-Next (180B MoE).
🔧 Rewired paths
🔹 12 full-attention layers · 🔹 36 linear-attention layers · 🔹 48 shared-expert layers — precision-strengthened
🔒 512 routed experts · router · vision encoder — untouched
→ Only 0.02% of the weights changed.
🔁 RSI × 🏛️ ZTC
RSI (recursive self-improvement): solve → verify against real answers → learn only the correct reasoning → repeat.
ZTC (Zero-Token Confidence): reads the model's internal state once, before answering, and returns the probability the answer is right — zero extra tokens. Returns answer + confidence as JSON.
{"answer": "...", "confidence": 0.97, "truncated": false}
✨ Synergy: ZTC finds where the model wavers → RSI learns exactly there → confidence gets sharper. Low confidence = stop, so agents don't act on wrong answers.
⚡ Same accuracy, 11% shorter reasoning — faster and cheaper.
📄 https://arxiv.org/abs/2605.14386
🤗 FINAL-Bench/Darwin-180B-RSI
🏛️ https://huggingface.co/collections/FINAL-Bench/ztc-models-jev-ecosystems
🏆 The result — #1 on five Hugging Face official leaderboards
🥇 AIME 2026 100% (first perfect score on the board)
🥇 HMMT Feb 2026 100% (first perfect score on the board)
🥇 GPQA Diamond 94.44%
🥇 MMLU-Pro 88.12%
🥇 MMMU-Pro 79.48%
📏 131K-token thinking budget · bf16 · samples per benchmark listed on the model card. 🚀
#Darwin #RSI #ZTC #AIME #HMMT #GPQA #MMLUPro #MMMUPro #OpenSource
👉 FINAL-Bench/Darwin-180B-RSI
🧬 Darwin — crossbreed and evolve the parent
Darwin diagnoses strong parent models like an MRI, inherits only their best parts, and evolves the weak spots — producing a child stronger than its parents.
Father model: Qwen3.8-Flash-Next (180B MoE).
🔧 Rewired paths
🔹 12 full-attention layers · 🔹 36 linear-attention layers · 🔹 48 shared-expert layers — precision-strengthened
🔒 512 routed experts · router · vision encoder — untouched
→ Only 0.02% of the weights changed.
🔁 RSI × 🏛️ ZTC
RSI (recursive self-improvement): solve → verify against real answers → learn only the correct reasoning → repeat.
ZTC (Zero-Token Confidence): reads the model's internal state once, before answering, and returns the probability the answer is right — zero extra tokens. Returns answer + confidence as JSON.
{"answer": "...", "confidence": 0.97, "truncated": false}
✨ Synergy: ZTC finds where the model wavers → RSI learns exactly there → confidence gets sharper. Low confidence = stop, so agents don't act on wrong answers.
⚡ Same accuracy, 11% shorter reasoning — faster and cheaper.
📄 https://arxiv.org/abs/2605.14386
🤗 FINAL-Bench/Darwin-180B-RSI
🏛️ https://huggingface.co/collections/FINAL-Bench/ztc-models-jev-ecosystems
🏆 The result — #1 on five Hugging Face official leaderboards
🥇 AIME 2026 100% (first perfect score on the board)
🥇 HMMT Feb 2026 100% (first perfect score on the board)
🥇 GPQA Diamond 94.44%
🥇 MMLU-Pro 88.12%
🥇 MMMU-Pro 79.48%
📏 131K-token thinking budget · bf16 · samples per benchmark listed on the model card. 🚀
#Darwin #RSI #ZTC #AIME #HMMT #GPQA #MMLUPro #MMMUPro #OpenSource
liked a
model 4 days ago
liked 4
models 5 days ago
ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF
Image-Text-to-Text • 177B • Updated • 96.1k • 79
munekazu/Qwen3.8-Flash-Next-exl3-CMP170HX-64GB
Image-Text-to-Text • 49B • Updated • 94 • 3
scorpoon/Swift-Qwen3.8-Flash-Next-exl3
Image-Text-to-Text • Updated • 32 • 2
ukisai/Swift1.5-Qwen3.8-Flash-Next
Image-Text-to-Text • 180B • Updated • 808 • 58
reacted to sharpenb's post with 🔥 5 days ago
Post
1851
Today, we open-source Pruna-Qwen-Image-2.1, a set of a few-step LoRA adapters that make Qwen-Image-2. up to 6.3× faster for image generation and editing.
Try it here: PrunaAI/Pruna-Qwen-Image-2.1
Try it here: PrunaAI/Pruna-Qwen-Image-2.1
liked 3
models 6 days ago
liked 5
models 7 days ago
bartowski/Ling-3.0-flash-VL-GGUF
Image-Text-to-Text • 124B • Updated • 3.14k • 12
benthecarman/MiMo-V2.6-Flash-RL-exl3
Text Generation • 46B • Updated • 1.47k • 8
bottlecapai/ThinkingCap-Qwen3.8-27B-NVFP4A4-AWQ
Image-Text-to-Text • 20B • Updated • 583 • 11
Comfy-Org/Ming-Image
Updated • 77.6k • 46
bottlecapai/ThinkingCap-Qwen3.8-27B
Image-Text-to-Text • 28B • Updated • 1.05k • 125
liked 2
models 8 days ago
