majentik
/

Qwen3.5-27B-RotorQuant-MLX-8bit

kv-cache-quantization

8-bit precision

Model card Files Files and versions

Qwen3.5-27B-RotorQuant-MLX-8bit

28.6 GB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

majentik's picture

Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache

e4515b3 verified 3 days ago

.gitattributes

1.57 kB
Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
README.md

2.88 kB
Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
chat_template.jinja

7.76 kB
Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
config.json

3.91 kB
Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
generation_config.json

244 Bytes
Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
model-00001-of-00006.safetensors

5.31 GB
xet

Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
model-00002-of-00006.safetensors

5.35 GB
xet

Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
model-00003-of-00006.safetensors

5.34 GB
xet

Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
model-00004-of-00006.safetensors

5.29 GB
xet

Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
model-00005-of-00006.safetensors

5.35 GB
xet

Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
model-00006-of-00006.safetensors

1.94 GB
xet

Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
model.safetensors.index.json

190 kB
Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
tokenizer.json

20 MB
xet

Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago
tokenizer_config.json

1.14 kB
Add MLX 8-bit quantized Qwen3.5-27B with RotorQuant KV cache 3 days ago