README
AX-DeepSeek-OCR-2-MLX-AXQ-6bit
Development AXQuant (AXQ) 6-bit language MLX pack of
deepseek-ai/DeepSeek-OCR-2
@ aaa02f3811945a91062062994c5c4a3f4c0af2b0.
Language experts/attention/MLP at 6-bit; vision towers BF16-preserved. Total BPW includes large BF16 vision (policy minimum ~8.3 when 4-bit is excluded).
Converted via MLX-VLM deepseekocr_2 from
mlx-community/DeepSeek-OCR-2-bf16
@ 9946f9ac306378a3e6a86cad7d7f8be8e536f092.
Claims
| Claim | Status |
|---|---|
| AXQuant architecture-prior / development quant | Yes |
| OCR accuracy / document-bench scores | Not claimed |
| Vision optimization | No — SAM + Qwen2 encoder + projector BF16-preserved |
| Certified release | No |
Attribution
Base weights © DeepSeek AI (Apache-2.0). Quantization by AXQuant (development).
Contributors
3 commits
Similar repos
README
AX-DeepSeek-OCR-2-MLX-AXQ-6bit
Development AXQuant (AXQ) 6-bit language MLX pack of
deepseek-ai/DeepSeek-OCR-2
@ aaa02f3811945a91062062994c5c4a3f4c0af2b0.
Language experts/attention/MLP at 6-bit; vision towers BF16-preserved. Total BPW includes large BF16 vision (policy minimum ~8.3 when 4-bit is excluded).
Converted via MLX-VLM deepseekocr_2 from
mlx-community/DeepSeek-OCR-2-bf16
@ 9946f9ac306378a3e6a86cad7d7f8be8e536f092.
Claims
| Claim | Status |
|---|---|
| AXQuant architecture-prior / development quant | Yes |
| OCR accuracy / document-bench scores | Not claimed |
| Vision optimization | No — SAM + Qwen2 encoder + projector BF16-preserved |
| Certified release | No |
Attribution
Base weights © DeepSeek AI (Apache-2.0). Quantization by AXQuant (development).
Similar repos
Linked in READMEs
Contributors
3 commits