inference-optimization/DeepSeek-V4-Pro-3.7B-A3.4B-small
Text Generation • 4B • Updated • 46
Small Models
Small versions of known models: same vLLM loading characteristics as the base, fewer layers/experts, identical hidden dims and hyperparameters
-
-
inference-optimization/Phi-3.5-MoE-1.0B-A0.7B-small
Text Generation • 1.0B • Updated • 42 -
inference-optimization/DeepSeek-V3-3.4B-A3.0B-small
Text Generation • 3B • Updated • 49 -
inference-optimization/Llama-3.2-0.5B-Instruct-small
Text Generation • 0.5B • Updated • 46 -
inference-optimization/Inkling-4.5B-A4.2B-small
Image-Text-to-Text • 5B • Updated • 43 -
inference-optimization/Qwen3-0.9B-A0.8B-small
Text Generation • 0.9B • Updated • 44 -
inference-optimization/granite-vision-4.1-0.6B-small
Image-Text-to-Text • 0.6B • Updated • 39 -
inference-optimization/Kimi-K3-4.6B-A4.5B-small
Feature Extraction • 5B • Updated • 35 -
inference-optimization/gemma-4-1.5B-A1.4B-small
Image-Text-to-Text • 1B • Updated • 34 -
inference-optimization/Qwen3-VL-Reranker-0.6B-small
Image-Text-to-Text • 0.6B • Updated • 32 -
inference-optimization/GLM-5.2-3.5B-A3.3B-small
Text Generation • 3B • Updated • 38 -
inference-optimization/Qwen3-VL-1.0B-A0.8B-small
Image-Text-to-Text • 1.0B • Updated • 35 -
inference-optimization/GLM-5.3-3.5B-A3.3B-small
Text Generation • 3B • Updated • 36 -
inference-optimization/Qwen3.8-Flash-Next-1.9B-A1.8B-small
Image-Text-to-Text • 2B • Updated • 38 -
inference-optimization/Qwen3.8-6.2B-A6.0B-small
Text Generation • 6B • Updated • 46 -
inference-optimization/Qwen3.6-1.3B-A1.3B-small
Image-Text-to-Text • 1B • Updated • 59 -
inference-optimization/NemotronH-3.4B-A3.4B-small
Text Generation • 3B • Updated • 31 -
inference-optimization/DeepSeek-V4-Flash-DSpark-2.1B-A1.9B-small
Text Generation • 2B • Updated • 54 -
inference-optimization/GLM-4.7-Flash-1.0B-A0.9B-small
Text Generation • 1B • Updated • 33 -
inference-optimization/GLM-5.3-Flash-2.6B-A2.3B-small
Image-Text-to-Text • 3B • Updated • 29 -
inference-optimization/gpt-oss-1.5B-A1.4B-small
Text Generation • 2B • Updated • 37 -
inference-optimization/gemma-4-unified-1.5B-small
Image-Text-to-Text • 2B • Updated • 35 -
inference-optimization/Llama-4-Scout-3.5B-A2.7B-small
Image-Text-to-Text • 4B • Updated • 25 -
inference-optimization/Nemotron-3.5-Lightning-0.9B-A0.8B-small
Text Generation • 0.9B • Updated • 30 -
inference-optimization/GLM-5-2.9B-A2.8B-small
Text Generation • 3B • Updated • 34