YihongJin
/

Qwen3-Omni-30B-A3B-Instruct-NVFP4-W4A16-awq

8-bit precision

Model card Files Files and versions

Qwen3-Omni-30B-A3B-Instruct-NVFP4-W4A16-awq

27.6 GB

Ctrl+K

Ctrl+K

1 contributor

History: 8 commits

YihongJin's picture

Remove --enforce-eager from serve command + cross-reference W4A4 siblings + vllm-omni#4025

a84959f verified 21 days ago

.gitattributes
1.57 kB
Initial upload: NVFP4 W4A16 (AWQ-clip calibration, 1024 prompts) 28 days ago
README.md
4.96 kB
Remove --enforce-eager from serve command + cross-reference W4A4 siblings + vllm-omni#4025 21 days ago
chat_template.json
6.77 kB
add chat_template.json (missing from ModelOpt export) 27 days ago
config.json
14.7 kB
Initial upload: NVFP4 W4A16 (AWQ-clip calibration, 1024 prompts) 28 days ago
generation_config.json
182 Bytes
Initial upload: NVFP4 W4A16 (AWQ-clip calibration, 1024 prompts) 28 days ago
hf_quant_config.json
387 Bytes
Add *mlp.gate*, *lm_head* to exclude_modules (ModelOpt export dropped these) 27 days ago
model-00001-of-00003.safetensors
10 GB
xet

Initial upload: NVFP4 W4A16 (AWQ-clip calibration, 1024 prompts) 28 days ago
model-00002-of-00003.safetensors
9.84 GB
xet

Initial upload: NVFP4 W4A16 (AWQ-clip calibration, 1024 prompts) 28 days ago
model-00003-of-00003.safetensors
7.71 GB
xet

Initial upload: NVFP4 W4A16 (AWQ-clip calibration, 1024 prompts) 28 days ago
model.safetensors.index.json
6.65 MB
Initial upload: NVFP4 W4A16 (AWQ-clip calibration, 1024 prompts) 28 days ago
preprocessor_config.json
603 Bytes
add preprocessor_config.json (missing from ModelOpt export) 27 days ago
tokenizer.json
11.4 MB
xet

Initial upload: NVFP4 W4A16 (AWQ-clip calibration, 1024 prompts) 28 days ago
tokenizer_config.json
957 Bytes
Initial upload: NVFP4 W4A16 (AWQ-clip calibration, 1024 prompts) 28 days ago