ModelListedExternal

GLM OCR OQ8 FP16

This model was quantized using oQ mixed-precision quantization.

Sourcehuggingface.co/RepublicOfKorokke/GLM-OCR-oQ8-fp16/tree/a022b88dff7e5846cec52dc3dc27d520fd3a37e6

KindText modelBase modelzai-org/GLM-OCRVersionmodelBgrade

Model source

Kind: Text model
File size: 1.48 GB
Base model: zai-org/GLM-OCR
Version: vmodel
Updated: Oct 31, 2026
Downloads: 69
Source: Hugging Face

Source description

GLM-OCR-oQ8-fp16

This model was quantized using oQ mixed-precision quantization.

float16 gives ~20% faster prefill on M1/M2 Apple Silicon (native fp16). bfloat16 is safer on M3/M4 and for numerical stability.

Benchmark (on M1 Max)

Model Variant	PP (Tokens per second)	TG (Tokens per second)
Original (bf16)	4,684	104.8
oQ8-fp16	3,806	99.0

Sources

1 source

Hugging FacePrimaryVersion a022b88dff7e5846cec52dc3dc27d520fd3a37e6

huggingface.co/RepublicOfKorokke/GLM-OCR-oQ8-fp16/tree/a022b88dff7e5846cec52dc3dc27d520fd3a37e6

Verified Aug 20

Model artifacts

1 artifact

model.safetensors

safetensors · 1.48 GB · SHA-256 d64c990014b0…d778 · Hugging Face

Download file

Source excerpts

2 excerpts

ReadmeAug 20huggingface.co/RepublicOfKorokke/GLM-OCR-oQ8-fp16

--- license: mit base_model: - zai-org/GLM-OCR pipeline_tag: image-to-text language: - zh - en - fr - es - ru - de - ja - ko tags: - mlx - oq - quantized library_name: mlx --- # GLM-OCR-oQ8-fp16 This model was quantized using [oQ](https://github.com/jundot/omlx) mixed-precision quantization. float16 gives ~20% faster prefill on M1/M2 Apple Silicon (native fp16). bfloat16 is safer on M3/M4 and for numerical stability. # Benchmark (on M1 Max) | Model Variant | PP (Tokens per second) | TG (Tokens per second) | | :--- | :---: | :---: | | Original (bf16) | 4,684 | 104.8 | | oQ8-fp16 | 3,806 | 99.0 |

NoteAug 20huggingface.co/RepublicOfKorokke/GLM-OCR-oQ8-fp16

Source context: 69 downloads · 3 likes · Pipeline image-to-text · Library mlx · Repo RepublicOfKorokke/GLM-OCR-oQ8-fp16