127 GB

Ctrl+K

1 contributor

History: 4 commits

majentik

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

bec0494 verified 25 days ago

.gitattributes

1.57 kB
Add MLX 8-bit quantized model with KV cache compression about 2 months ago
README.md

5.9 kB
docs: Tier 2 polish — variant matrix + quant trade-off 25 days ago
config.json

11 kB
Add MLX 8-bit quantized model with KV cache compression about 2 months ago
generation_config.json

132 Bytes
Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00001-of-00028.safetensors

4.91 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00002-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00003-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00004-of-00028.safetensors

4.68 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00005-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00006-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00007-of-00028.safetensors

4.68 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00008-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00009-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00010-of-00028.safetensors

4.68 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00011-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00012-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00013-of-00028.safetensors

4.68 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00014-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00015-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00016-of-00028.safetensors

4.68 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00017-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00018-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00019-of-00028.safetensors

4.68 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00020-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00021-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00022-of-00028.safetensors

4.68 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00023-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00024-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00025-of-00028.safetensors

4.68 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00026-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00027-of-00028.safetensors

4.62 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model-00028-of-00028.safetensors

1.74 GB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
model.safetensors.index.json

182 kB
Add MLX 8-bit quantized model with KV cache compression about 2 months ago
processor_config.json

660 Bytes
Add MLX 8-bit quantized model with KV cache compression about 2 months ago
tokenizer.json

17.1 MB
xet

Add MLX 8-bit quantized model with KV cache compression about 2 months ago
tokenizer_config.json

21.2 kB
Add MLX 8-bit quantized model with KV cache compression about 2 months ago