mattbucci
/

Qwen3-30B-Instruct-2507-REAM-AWQ

4-bit precision

Model card Files Files and versions

Qwen3-30B-Instruct-2507-REAM-AWQ

13.1 GB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

mattbucci's picture

fix: render OpenAI structured (list) content instead of blanking it — string-only guard made agentic clients run blind (empty task + tool responses)

babe5d9 verified 18 days ago

.gitattributes

1.57 kB
Qwen3-30B-Instruct-2507 REAM (96 exp) AWQ — in-house rebuild, basic PASS @ 256K 2 months ago
chat_template.jinja

3.07 kB
fix: render OpenAI structured (list) content instead of blanking it — string-only guard made agentic clients run blind (empty task + tool responses) 18 days ago
config.json

1.76 kB
Qwen3-30B-Instruct-2507 REAM (96 exp) AWQ — in-house rebuild, basic PASS @ 256K 2 months ago
generation_config.json

212 Bytes
Qwen3-30B-Instruct-2507 REAM (96 exp) AWQ — in-house rebuild, basic PASS @ 256K 2 months ago
model.safetensors

13 GB
xet

Qwen3-30B-Instruct-2507 REAM (96 exp) AWQ — in-house rebuild, basic PASS @ 256K 2 months ago
model.safetensors.index.json

3.18 MB
Qwen3-30B-Instruct-2507 REAM (96 exp) AWQ — in-house rebuild, basic PASS @ 256K 2 months ago
tokenizer.json

11.4 MB
xet

Qwen3-30B-Instruct-2507 REAM (96 exp) AWQ — in-house rebuild, basic PASS @ 256K 2 months ago
tokenizer_config.json

349 Bytes
Qwen3-30B-Instruct-2507 REAM (96 exp) AWQ — in-house rebuild, basic PASS @ 256K 2 months ago