全站搜索
AI 模型 84762
- HaS_Text_0209_0.6B_Q8↗
xuanwulab
- gemma4-12B-it-DFlash↗
z-lab
- Gemma-4-E4B-DECKARD-HERETIC-NVFP4↗
AEON-7
- DataDecide-dolma1_7-20M↗
allenai
- EthicalEye↗
autopilot-ai
- Qwen3.8-27B-NVFP4-DGX-SPARK↗
autotrust
A **lossless speed distribution** of `nvidia/Qwen3.8-27B-NVFP4`: the exact same weights, shipped with a fully benchmark-tuned MTP speculative decoding setup. Single-stream decode on a DGX Spark (GB10) goes from **12.5 → 48.2 tok/s (3.9×)**. Screen recording on a DGX Spark: a coding benchmark script streams the model's reasoning and code, then executes the generated program and checks its output (dgx_spark_demo.mov, 4 min 49 s). The same weights and drafter recipe on one NVIDIA B200 (vLLM 0.31.0 OpenAI server, single stream, temperature 0, MTP k=7 — the best setting on B200; k=8 is best on Spark). Four coding tasks: the model streams its thinking and code, then the generated program is executed against tests (all pass). The video is a real-time replay of the measured token arrival times (no speed-up or cuts); token counts include thinking + answer.
- NaijaVox-2.0↗
Axiveri
- Artemis-31B-v1q-GGUF↗
BeaverAI
- Qwen3-4B-AgentCoder↗
br1-pist
- Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16↗
chaoliangUNSW
