3.22 GB

Ctrl+K

1 contributor

History: 3 commits

majentik

docs: Tier 2 polish — variant matrix + quant trade-off

f2d00ab verified 27 days ago

.gitattributes

1.63 kB
Add MLX quantized model with KV cache compression about 2 months ago
README.md

5.34 kB
docs: Tier 2 polish — variant matrix + quant trade-off 27 days ago
adaptor.safetensors

439 MB
xet

Add MLX quantized model with KV cache compression about 2 months ago
adaptor_config.json

82 Bytes
Add MLX quantized model with KV cache compression about 2 months ago
config.json

2.79 kB
Add MLX quantized model with KV cache compression about 2 months ago
decoder-00000.safetensors

1.47 GB
xet

Add MLX quantized model with KV cache compression about 2 months ago
decoder.safetensors.index.json

49.3 kB
Add MLX quantized model with KV cache compression about 2 months ago
decoder_config.json

975 Bytes
Add MLX quantized model with KV cache compression about 2 months ago
encoder.safetensors

1.27 GB
xet

Add MLX quantized model with KV cache compression about 2 months ago
encoder_config.json

1.21 kB
Add MLX quantized model with KV cache compression about 2 months ago
generation_config.json

197 Bytes
Add MLX quantized model with KV cache compression about 2 months ago
preprocessor_config.json

443 Bytes
Add MLX quantized model with KV cache compression about 2 months ago
processor_config.json

281 Bytes
Add MLX quantized model with KV cache compression about 2 months ago
special_tokens_map.json

636 Bytes
Add MLX quantized model with KV cache compression about 2 months ago
tokenizer.json

34.4 MB
xet

Add MLX quantized model with KV cache compression about 2 months ago
tokenizer.model

4.24 MB
xet

Add MLX quantized model with KV cache compression about 2 months ago
tokenizer_config.json

46.9 kB
Add MLX quantized model with KV cache compression about 2 months ago