view article Article Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps +1 iamleonie, burtenshaw, sergiopaniego • 30 days ago • 145
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution Paper • 2608.16157 • Published Aug 17 • 112
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF Text Generation • 12B • Updated Jun 19 • 406k • 2.92k
Running 12 Qwopus3.6-35B-A3B-v1 Evaluation 🧪 12 Hands-on eval of Jackrong/Qwopus3.6-35B-A3B-v1 (Q5_K_M GGUF)
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift • Apr 2 • 930
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Paper • 2604.04921 • Published Apr 6 • 113
Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF Text Generation • 4B • Updated Apr 6 • 154k • 170