mattbucci
/

Qwen3-Coder-30B-A3B-AWQ

4-bit precision

Model card Files Files and versions

Qwen3-Coder-30B-A3B-AWQ

16.8 GB

Ctrl+K

Ctrl+K

1 contributor

History: 8 commits

mattbucci's picture

Upload config.json with huggingface_hub

6531bac verified 4 months ago

.gitattributes

1.57 kB
Qwen3 Coder 30B MoE AWQ: 128 experts, 30 tok/s on RDNA4 6 months ago
README.md

1.43 kB
Add model card for Qwen3-Coder-30B MoE AWQ 4-bit 6 months ago
added_tokens.json

707 Bytes
Qwen3 Coder 30B MoE AWQ: 128 experts, 30 tok/s on RDNA4 6 months ago
chat_template.jinja

6.84 kB
fix: parse tool_call.arguments JSON-string before |items (3090 SWE-bench bug) 5 months ago
config.json

1.24 kB
Upload config.json with huggingface_hub 4 months ago
generation_config.json

216 Bytes
Add files using upload-large-folder tool 5 months ago
merges.txt

1.67 MB
Qwen3 Coder 30B MoE AWQ: 128 experts, 30 tok/s on RDNA4 6 months ago
model.safetensors

16.8 GB
xet

Upload folder using huggingface_hub 4 months ago
model.safetensors.index.json

4.24 MB
Upload folder using huggingface_hub 4 months ago
qwen3coder_tool_parser.py

28.9 kB
Qwen3 Coder 30B MoE AWQ: 128 experts, 30 tok/s on RDNA4 6 months ago
recipe.yaml

306 Bytes
Add files using upload-large-folder tool 5 months ago
special_tokens_map.json

613 Bytes
Qwen3 Coder 30B MoE AWQ: 128 experts, 30 tok/s on RDNA4 6 months ago
tokenizer.json

11.4 MB
xet

Add files using upload-large-folder tool 5 months ago
tokenizer_config.json

666 Bytes
Add files using upload-large-folder tool 5 months ago
vocab.json

2.78 MB
Qwen3 Coder 30B MoE AWQ: 128 experts, 30 tok/s on RDNA4 6 months ago