nm-testing/Qwen3-VL-4B-Instruct-NVFP4
3B • Updated • 84
• 2
nm-testing/Llama-3.1-8B-Instruct-NVFP4-mse
5B • Updated • 15
nm-testing/Llama-3.1-8B-Instruct-NVFP4-static_minmax
5B • Updated • 14
nm-testing/EAGLE3-LLaMA3.1-Instruct-8B-sgl
0.4B • Updated • 22
nm-testing/Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16-sgl
1B • Updated • 43
nm-testing/SpeculatorLlama3-1-8B-Eagle3-sgl
1.0B • Updated • 29
nm-testing/Mockup-qwen235-eagle3-fp16-sgl
1B • Updated • 16
nm-testing/Speculator-Qwen3-8B-Eagle3-sgl
1B • Updated • 55
nm-testing/Qwen3-VL-235B-A22B-Instruct-NVFP4
Updated
nm-testing/Mockup-qwen235-eagle3-fp16-speculators-converted
1B • Updated • 40
nm-testing/Llama-3.1-70B-Instruct-FP8-block
Text Generation • Updated nm-testing/Qwen3-235B-A22B-EAGLE3-converted-speculators-lmsys
1B • Updated • 41
nm-testing/Qwen2.5-VL-7B-Instruct-INT8_dyn_per_token
8B • Updated • 16
nm-testing/Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16
1B • Updated • 629
nm-testing/llama-3.3-70b-speculators-eagle3
2B • Updated • 43
nm-testing/Qwen3-30B-A3B-NVFP4-working
17B • Updated • 33
nm-testing/Meta-Llama-3-8B-Instruct-selfattn-w8a8-mlp-w4a16-sequential
3B • Updated • 14
nm-testing/for_testing_gptoss20b_spec_eagle3
0.8B • Updated • 18
nm-testing/Apertus-8B-Instruct-2509-NVFP4
5B • Updated • 15
nm-testing/Llama-3.2-1B-Instruct-quip-w4a16
2B • Updated • 387
nm-testing/gemma-3-4b-it-s_q-W4A8-G512
5B • Updated • 14
nm-testing/llama3.3-70B-speculators.09-10-2025-eagle3
2B • Updated • 32
nm-testing/Llama-3.2-1B-Instruct-quipv-w4a16
2B • Updated • 11
nm-testing/Llama-3.2-1B-Instruct-quip
2B • Updated • 10
nm-testing/Llama-3.2-1B-Instruct-spinquantR1R2-online
2B • Updated • 15
nm-testing/Qwen3-Coder-30B-A3B-Instruct-W4A16-awq
5B • Updated • 25.9k
• 4
nm-testing/llama4-scout-17b-eagle3-dummy-drafter
0.6B • Updated • 44
nm-testing/Llama-3.2-1B-Instruct-spinquantR1R2R4-w4a16
2B • Updated • 463
nm-testing/Llama-3.1-8B-Instruct-quip-w4a16
2B • Updated • 15
nm-testing/Meta-Llama-3-8B-Instruct-spinquantR3
8B • Updated • 11