Inference Optimization

community

AI & ML interests

None defined yet.

Recent Activity

nm-research updated a model about 2 hours ago

inference-optimization/Qwen3-30B-from-self-speculators.eagle3-ckpt5

nm-research updated a model about 2 hours ago

inference-optimization/Qwen3-32B-from-self-speculators.eagle3-ckpt4

nm-research published a model about 2 hours ago

inference-optimization/Qwen3-32B-from-self-speculators.eagle3-ckpt4

View all activity

inference-optimization 's models 192

inference-optimization/Qwen3-0.6B-debug-add

0.6B • Updated Jan 23

inference-optimization/Qwen3-0.6B-debug-multiply

0.6B • Updated Jan 23

inference-optimization/DeepSeek-V3-debug-empty

1B • Updated Jan 23 • 35

inference-optimization/granite-4.0-h-tiny-FP8-block

Text Generation • 7B • Updated Jan 23 • 5

inference-optimization/granite-4.0-h-tiny-quantized.w8a8

7B • Updated Jan 23 • 3

inference-optimization/granite-4.0-h-tiny-NVFP4

inference-optimization/granite-4.0-h-tiny-quantized.w4a16

Updated Jan 22 • 1

inference-optimization/granite-4.0-h-small-quantized.w8a8

inference-optimization/granite-4.0-h-small-NVFP4

inference-optimization/granite-4.0-h-small-quantized.w4a16

inference-optimization/granite-4.0-h-small-FP8-dynamic

inference-optimization/granite-4.0-h-small-FP8-block

inference-optimization/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4

18B • Updated Jan 15 • 1

inference-optimization/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8

Text Generation • 32B • Updated Jan 9 • 7

inference-optimization/Qwen3-Next-80B-A3B-Thinking-FP8

Text Generation • 81B • Updated Jan 9 • 9

inference-optimization/Qwen3-Next-80B-A3B-Instruct-FP8

Text Generation • 81B • Updated Jan 9 • 8

inference-optimization/NVIDIA-Nemotron-3-Nano-30B-A3B-quantized.w4a16

6B • Updated Jan 7 • 2

inference-optimization/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8-dynamic

32B • Updated Jan 6 • 1

inference-optimization/Qwen3-Next-80B-A3B-Thinking-quantized.w8a8

Updated Dec 24, 2025

inference-optimization/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8-block

Updated Dec 22, 2025

inference-optimization/Llama-3.1-8B-Instruct-FP8-dynamic-QKV-Cache-FP8-Per-Head

8B • Updated Dec 11, 2025 • 2

inference-optimization/Llama-3.1-8B-Instruct-QKV-Cache-FP8-Per-Head

8B • Updated Dec 10, 2025 • 2

inference-optimization/Qwen3-Next-80B-A3B-Instruct-quantized.w8a8

Updated Dec 9, 2025

inference-optimization/Llama-3.1-8B-Instruct-HIGGS-quantized-paths

Updated Dec 8, 2025

inference-optimization/Llama-3.1-8B-Instruct-Mixed-NVFP4-FP8_DYNAMIC-gate_up_proj-all

7B • Updated Dec 4, 2025 • 2

inference-optimization/Llama-3.1-8B-Instruct-Mixed-NVFP4-FP8_DYNAMIC-down_proj-all

6B • Updated Dec 4, 2025 • 2

inference-optimization/Llama-3.1-8B-Instruct-Mixed-NVFP4-FP8_DYNAMIC-qkv_proj-all

5B • Updated Dec 4, 2025 • 2

inference-optimization/Llama-3.1-8B-Instruct-Mixed-NVFP4-FP8_DYNAMIC-out_proj-all

5B • Updated Dec 4, 2025 • 2

inference-optimization/Llama-3.1-8B-Instruct-Mixed-NVFP4-FP8_BLOCK-gate_up_proj-all

7B • Updated Dec 4, 2025 • 5

inference-optimization/Llama-3.1-8B-Instruct-Mixed-NVFP4-FP8_BLOCK-down_proj-all

6B • Updated Dec 4, 2025 • 1