GLM-5.3-Flash-oQ6e-mtp
[!NOTE] Updated 2026-10-29: Re-quantized with the improved oQe quantization in oMLX 0.7.3. Please re-download if you have an earlier copy.
This model was quantized using oQ (oMLX v0.7.3) mixed-precision quantization with improved oQe (jundot/omlx#4930).
A mixed-precision MLX checkpoint of zai-org/GLM-5.3-Flash, a natively multimodal mixture-of-experts model with 320B total and 18B active parameters that combines sparse and linear attention with Manifold-Constrained Hyper-Connections (mHC). It includes the language model, the vision encoder and the multi-token prediction (MTP) head.
The effective average is 6.564 bits/weight for the language backbone and 6.581 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 | 311.654B | 96.991% | 235.828 GiB | 6.50 |
| Affine 8-bit, group 64 | 8.976B | 2.793% | 8.882 GiB | 8.50 |
| BF16 | 0.607B | 0.189% | 1.131 GiB | 16.00 |
| FP32 | 0.086B | 0.027% | 0.322 GiB | 32.00 |
| Total | 321.323B | 100% | 246.163 GiB | 6.581 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language backbone | 313.327B | 257.068 GB / 239.413 GiB |
| Vision encoder | 0.564B | 1.127 GB / 1.050 GiB |
| MTP head | 7.433B | 6.121 GB / 5.700 GiB |
| Total | 321.323B | 264.315 GB / 246.163 GiB |
License
MIT, following the source model. See LICENSE.