nullrunner
/

Qwen3-32B-EXL3-4.0bpw

Text Generation

4-bit precision

Model card Files Files and versions

Qwen3-32B-EXL3-4.0bpw

18 GB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

nullrunner's picture

Fix calibration dataset info: CTO Mix V3 (~550 samples)

891467d verified 6 months ago

.gitattributes

1.57 kB
Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
LICENSE

11.3 kB
Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
README.md

3.15 kB
Fix calibration dataset info: CTO Mix V3 (~550 samples) 6 months ago
config.json

1.07 kB
Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
generation_config.json

239 Bytes
Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
merges.txt

1.67 MB
Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
model-00001-of-00003.safetensors

8.39 GB
xet

Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
model-00002-of-00003.safetensors

8.54 GB
xet

Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
model-00003-of-00003.safetensors

1.02 GB
xet

Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
model.safetensors.index.json

172 kB
Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
quantization_config.json

621 kB
Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
tokenizer.json

11.4 MB
xet

Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
tokenizer_config.json

9.73 kB
Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago
vocab.json

2.78 MB
Qwen3-32B quantized to EXL3 4.0bpw (8bpw head) 6 months ago