clef-flash-oQ8e
This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization (jundot/omlx#4385).
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 8.955 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
oQ8e 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 8-bit, group 64 | 8.953B | 93.927% | 8.859 GiB | 8.50 |
| BF16 | 0.579B | 6.073% | 1.078 GiB | 16.00 |
| Total | 9.532B | 100% | 9.937 GiB | 8.955 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language backbone | 8.954B | 9.514 GB / 8.861 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 | 10.670 GB / 9.937 GiB |
License
Apache-2.0, following the source model. See LICENSE.