-
inference-optimization/Qwen3-8B-DFlash-Gauss-FP8-W8A8
Text Generation • 1B • Updated • 59 -
inference-optimization/Qwen3-8B-DFlash-PerfectBlend-FP8-W8A8
Text Generation • 1B • Updated • 53 -
inference-optimization/Qwen3-8B-DFlash-Gauss-NVFP4-W4A4
Text Generation • 1B • Updated • 164 -
inference-optimization/Qwen3-8B-DFlash-PerfectBlend-NVFP4-W4A4
Text Generation • 1B • Updated • 158
Inference Optimization
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Tiny models used for testing
-
inference-optimization/gemma-4-1B-0.8B-tiny
1B • Updated • 1.37k • 2 -
inference-optimization/DSV4-tiny-empty
3B • Updated • 2.59k • 1 -
inference-optimization/Qwen3-1.6B-A0.9B
Text Generation • 2B • Updated • 8.89k • 3 -
inference-optimization/Llama-3.2-0.5B-Instruct
Text Generation • 0.5B • Updated • 10.4k • 1
Models used in CI tests across llm-compressor, compressed-tensors, and vllm repositories.
-
inference-optimization/DSV4-tiny-empty
3B • Updated • 2.59k • 1 -
inference-optimization/GLM-5.2-0.8B-A0.8B
Text Generation • 0.8B • Updated • 2.74k • 4 -
inference-optimization/Llama-3.2-0.5B-Instruct
Text Generation • 0.5B • Updated • 10.4k • 1 -
inference-optimization/Qwen3-1.6B-A0.9B
Text Generation • 2B • Updated • 8.89k • 3
Toy-trained BF16/FP8 fixtures for PR #3225 on Transformers 5.17. Model cards document DSA and Inkling limitations.
-
inference-optimization/GLM-4.7-Flash-0.82B-MTP
Text Generation • 0.8B • Updated • 22 -
inference-optimization/DeepSeek-V3-0.86B-MTP
Text Generation • 0.9B • Updated • 20 -
inference-optimization/GLM-5-0.88B-MTP
Text Generation • 0.9B • Updated • 19 -
inference-optimization/Inkling-0.92B-MTP
Image-Text-to-Text • 0.9B • Updated • 42
-
inference-optimization/Qwen3-8B-DFlash-Gauss-FP8-W8A8
Text Generation • 1B • Updated • 59 -
inference-optimization/Qwen3-8B-DFlash-PerfectBlend-FP8-W8A8
Text Generation • 1B • Updated • 53 -
inference-optimization/Qwen3-8B-DFlash-Gauss-NVFP4-W4A4
Text Generation • 1B • Updated • 164 -
inference-optimization/Qwen3-8B-DFlash-PerfectBlend-NVFP4-W4A4
Text Generation • 1B • Updated • 158
Models used in CI tests across llm-compressor, compressed-tensors, and vllm repositories.
-
inference-optimization/DSV4-tiny-empty
3B • Updated • 2.59k • 1 -
inference-optimization/GLM-5.2-0.8B-A0.8B
Text Generation • 0.8B • Updated • 2.74k • 4 -
inference-optimization/Llama-3.2-0.5B-Instruct
Text Generation • 0.5B • Updated • 10.4k • 1 -
inference-optimization/Qwen3-1.6B-A0.9B
Text Generation • 2B • Updated • 8.89k • 3
Tiny models used for testing
-
inference-optimization/gemma-4-1B-0.8B-tiny
1B • Updated • 1.37k • 2 -
inference-optimization/DSV4-tiny-empty
3B • Updated • 2.59k • 1 -
inference-optimization/Qwen3-1.6B-A0.9B
Text Generation • 2B • Updated • 8.89k • 3 -
inference-optimization/Llama-3.2-0.5B-Instruct
Text Generation • 0.5B • Updated • 10.4k • 1
Toy-trained BF16/FP8 fixtures for PR #3225 on Transformers 5.17. Model cards document DSA and Inkling limitations.
-
inference-optimization/GLM-4.7-Flash-0.82B-MTP
Text Generation • 0.8B • Updated • 22 -
inference-optimization/DeepSeek-V3-0.86B-MTP
Text Generation • 0.9B • Updated • 20 -
inference-optimization/GLM-5-0.88B-MTP
Text Generation • 0.9B • Updated • 19 -
inference-optimization/Inkling-0.92B-MTP
Image-Text-to-Text • 0.9B • Updated • 42