clef-flash-oQ6e

Updated 2026-11-19: Re-quantized with the refined oQe rounding in oMLX 0.8.0, which lowers quantization error at the same size and speed. Please re-download if you have an earlier copy.

This model was quantized using oQ (oMLX v0.8.0) mixed-precision quantization with improved oQe (jundot/omlx#4930) and oQe rounding refinement (jundot/omlx#5292).

A mixed-precision MLX checkpoint of Cloudflare/clef-flash, a 9B decision model post-trained from Qwen/Qwen3.5-9B that turns a state and a schema of typed questions into decisions, returning a probability for every allowed option of every question in a single forward pass. It includes the Qwen3.5-9B language backbone, the vision encoder and the joint schema head.

The joint schema head (joint_head.safetensors, joint_head_config.json) is copied unchanged from the source. oMLX serves this checkpoint through POST /v1/systemone.

The effective average is 6.700 bits/weight for the language backbone and 7.264 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

oQ6e allocates bits by measured layer sensitivity, then rounds each group with an importance matrix (128 samples x 512 tokens) and a weighted least-squares refit of its scale and bias.

Storage format Logical weights Share of total Tensor storage Effective bits/weight
Affine 6-bit, group 64 8.061B 84.574% 6.100 GiB 6.50
Affine 8-bit, group 64 0.892B 9.354% 0.882 GiB 8.50
BF16 0.579B 6.073% 1.078 GiB 16.00
Total 9.532B 100% 8.060 GiB 7.264

Storage Breakdown

Component Logical weights Storage
Language backbone 8.954B 7.499 GB / 6.984 GiB
Vision encoder 0.456B 0.912 GB / 0.849 GiB
Joint schema head 0.122B 0.244 GB / 0.227 GiB
Total 9.532B 8.655 GB / 8.060 GiB

License

Apache-2.0, following the source model. See LICENSE.

Downloads last month
141
Safetensors
Model size
9B params
Tensor type
U32
ยท
BF16
ยท
MLX
Hardware compatibility
Log In to add your hardware

6-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Jundot/clef-flash-oQ6e

Finetuned
Qwen/Qwen3.5-9B
Quantized
(64)
this model