Hugging Face model directory
inference-optimization
Inference Optimization
508 public models. Explore architecture graphs, discover recent releases, and find your next model.
inference-optimization on Hugging Face ↗
Watch inference-optimization releases
-
Qwen3-30B-A3B-FP8
↓ 0 downloads♡ 0 likes -
Qwen3.8-Flash-Next-1.9B-A1.8B-small
↓ 53 downloads♡ 0 likes -
GLM-5-2.9B-A2.8B-small
↓ 43 downloads♡ 0 likes -
GLM-5.3-3.5B-A3.3B-small
↓ 43 downloads♡ 0 likes -
Nemotron-3.5-Lightning-0.9B-A0.8B-small
↓ 34 downloads♡ 0 likes -
Llama-4-Scout-3.5B-A2.7B-small
↓ 27 downloads♡ 0 likes -
Qwen3-VL-1.0B-A0.8B-small
↓ 37 downloads♡ 0 likes -
gemma-4-unified-1.5B-small
↓ 39 downloads♡ 0 likes -
GLM-5.2-3.5B-A3.3B-small
↓ 44 downloads♡ 0 likes -
Qwen3-VL-Reranker-0.6B-small
↓ 41 downloads♡ 0 likes -
gemma-4-1.5B-A1.4B-small
↓ 39 downloads♡ 0 likes -
Kimi-K3-4.6B-A4.5B-small
↓ 42 downloads♡ 0 likes -
gpt-oss-1.5B-A1.4B-small
↓ 40 downloads♡ 0 likes -
GLM-5.3-Flash-2.6B-A2.3B-small
↓ 40 downloads♡ 1 like -
granite-vision-4.1-0.6B-small
↓ 50 downloads♡ 0 likes -
Qwen3-0.9B-A0.8B-small
↓ 51 downloads♡ 0 likes -
GLM-4.7-Flash-1.0B-A0.9B-small
↓ 39 downloads♡ 0 likes -
Inkling-4.5B-A4.2B-small
↓ 48 downloads♡ 0 likes -
DeepSeek-V4-Flash-DSpark-2.1B-A1.9B-small
↓ 65 downloads♡ 0 likes -
Llama-3.2-0.5B-Instruct-small
↓ 49 downloads♡ 0 likes -
NemotronH-3.4B-A3.4B-small
↓ 39 downloads♡ 0 likes -
DeepSeek-V3-3.4B-A3.0B-small
↓ 57 downloads♡ 0 likes -
Qwen3.6-1.3B-A1.3B-small
↓ 627 downloads♡ 0 likes -
Phi-3.5-MoE-1.0B-A0.7B-small
↓ 50 downloads♡ 0 likes -
Qwen3.8-6.2B-A6.0B-small
↓ 50 downloads♡ 0 likes -
DeepSeek-V4-Pro-3.7B-A3.4B-small
↓ 53 downloads♡ 0 likes -
Qwen3-1.6B-A0.9B-FP8-REAP-15-uniform
↓ 20 downloads♡ 0 likes -
Qwen3-1.6B-A0.9B-FP8-REAP-15-nonuniform
↓ 24 downloads♡ 0 likes -
Qwen3-30B-A3B-FP8-REAP-15-nonuniform
↓ 30 downloads♡ 0 likes -
Qwen3-30B-A3B-FP8-REAP-15-uniform
↓ 31 downloads♡ 0 likes -
dflash2-qwen38-27b-regen-test
↓ 0 downloads♡ 0 likes -
qwe3.8-27B-perfectblend_replace_25ksteps_ckpt0
↓ 0 downloads♡ 0 likes -
qwen3.8-27B-speculator.dflash2.updatedparams.epoch1_end
↓ 0 downloads♡ 0 likes -
Inkling-0.92B-MTP
↓ 46 downloads♡ 0 likes -
GLM-5-0.88B-MTP
↓ 25 downloads♡ 0 likes -
DeepSeek-V3-0.86B-MTP
↓ 25 downloads♡ 0 likes -
GLM-4.7-Flash-0.82B-MTP
↓ 26 downloads♡ 0 likes -
gemma-4-31b-it-speculator.dflash.latestrecipe.ckpt2
↓ 44 downloads♡ 0 likes -
qwen38-dspark-cooldown-fineweb
↓ 45 downloads♡ 0 likes -
qwen38-dspark-pretrain-fineweb
↓ 60 downloads♡ 0 likes -
Qwen3-30B-A3B-Thinking-2507-REAP-25-nonuniform
↓ 192 downloads♡ 0 likes -
Qwen3-30B-A3B-Thinking-2507-REAP-25-uniform
↓ 338 downloads♡ 1 like -
qwen3.8-27B-speculator.dflash2.comparisonrecipe.v2.epoch1_end
↓ 187 downloads♡ 0 likes -
gemma-4-31B-it-speculator.dflash.latestrecipe.bs8.ckp0
↓ 62 downloads♡ 0 likes -
Qwen3.8-27B-DSpark-GPTQ-IMatrix-PerfectBlend-NVFP4-W4A4
↓ 157 downloads♡ 0 likes -
Qwen3.8-27B-DSpark-GPTQ-IMatrix-Gauss-NVFP4-W4A4
↓ 152 downloads♡ 0 likes -
Qwen3.8-27B-DSpark-GPTQ-PerfectBlend-NVFP4-W4A4
↓ 148 downloads♡ 0 likes -
Qwen3.8-27B-DSpark-GPTQ-Gauss-NVFP4-W4A4
↓ 149 downloads♡ 0 likes -
Qwen3.8-27B-DSpark-PerfectBlend-NVFP4-W4A4
↓ 302 downloads♡ 0 likes -
Qwen3.8-27B-DSpark-Gauss-NVFP4-W4A4
↓ 296 downloads♡ 0 likes -
Qwen3.8-27B-DSpark-PerfectBlend-FP8-W8A8
↓ 114 downloads♡ 0 likes -
Qwen3.8-27B-DSpark-Gauss-FP8-W8A8
↓ 116 downloads♡ 0 likes -
Qwen3.8-27B-DSpark-FP8-DYNAMIC
↓ 133 downloads♡ 0 likes -
Qwen3.8-27B-DSpark-FP8-BLOCK
↓ 115 downloads♡ 0 likes -
qwen3.8-27B-speculator.dflash2.comparisonrecipe.v2.epoch1_step107505
↓ 79 downloads♡ 0 likes -
Qwen3-8B-DFlash-GPTQ-IMatrix-PerfectBlend-NVFP4-W4A4
↓ 99 downloads♡ 0 likes -
Qwen3-8B-DFlash-GPTQ-IMatrix-Gauss-NVFP4-W4A4
↓ 95 downloads♡ 0 likes -
Qwen3-8B-DFlash-GPTQ-PerfectBlend-NVFP4-W4A4
↓ 91 downloads♡ 0 likes -
Qwen3-8B-DFlash-GPTQ-Gauss-NVFP4-W4A4
↓ 90 downloads♡ 0 likes -
Qwen3-8B-DFlash-FP8-BLOCK
↓ 70 downloads♡ 0 likes