A mixed-precision MLX checkpoint of internlm/Sage-S2.1-Flash (Shanghai AI Laboratory / InternLM), a fine-tune of GLM-5.3-Flash with the same architecture: a natively multimodal mixture-of-experts model with 320B total and 18B active parameters.
It was quantized with oQ (oMLX v0.7.4.dev1) from the official FP8 release, internlm/Sage-S2.1-Flash-FP8 at revision 716e6436905650b7be93e1b7dedfb0bb95afd3a3, using the same recipe as Jundot/GLM-5.3-Flash-oQ4e-mtp: oQ4e, with the MTP head preserved.
The effective average is 4.641 bits/weight for the complete checkpoint, the same layout as that GLM pack.
oQ4e 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.
One difference from the GLM pack's build: oMLX 0.7.4.dev1 streams this architecture's calibration one decoder layer at a time from the FP8 source, where the GLM pack (oMLX v0.7.3.dev1) calibrated on a temporary 4-bit proxy.
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 4-bit, group 64 | 311.654B | 96.991% | 163.266 GiB | 4.50 |
| 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% | 173.600 GiB | 4.641 |
| Component | Logical weights | Storage |
|---|---|---|
| Language backbone | 313.327B | 180.966 GB / 168.538 GiB |
| Vision encoder | 0.564B | 1.127 GB / 1.050 GiB |
| MTP head | 7.433B | 4.309 GB / 4.013 GiB |
| Total | 321.323B | 186.402 GB / 173.600 GiB |
MIT, following the source model. Sage-S2.1-Flash's code and weights are released under the MIT License by Shanghai AI Laboratory / InternLM. Sage-S2.1-Flash is built on GLM-5.3-Flash, whose MIT license notice (Z.AI) is included as LICENSE.
model-00002-of-00035.safetensors 5.9 GBmodel-00034-of-00035.safetensors 5.6 GBmodel-00018-of-00035.safetensors 5.5 GBmodel-00021-of-00035.safetensors 5.5 GBmodel-00024-of-00035.safetensors 5.5 GBmodel-00027-of-00035.safetensors 5.5 GBmodel-00030-of-00035.safetensors 5.5 GBmodel-00033-of-00035.safetensors 5.5 GBmodel-00012-of-00035.safetensors 5.5 GBmodel-00015-of-00035.safetensors 5.5 GBmodel-00009-of-00035.safetensors 5.5 GBmodel-00006-of-00035.safetensors 5.5 GBmodel-00003-of-00035.safetensors 5.5 GBmodel-00017-of-00035.safetensors 5.4 GBmodel-00014-of-00035.safetensors 5.4 GBmodel-00020-of-00035.safetensors 5.4 GBmodel-00008-of-00035.safetensors 5.4 GBmodel-00019-of-00035.safetensors 5.4 GBmodel-00023-of-00035.safetensors 5.4 GBmodel-00032-of-00035.safetensors 5.4 GBmodel-00011-of-00035.safetensors 5.4 GBmodel-00010-of-00035.safetensors 5.4 GBmodel-00013-of-00035.safetensors 5.4 GBmodel-00025-of-00035.safetensors 5.4 GBmodel-00026-of-00035.safetensors 5.4 GBmodel-00028-of-00035.safetensors 5.4 GBmodel-00016-of-00035.safetensors 5.4 GBmodel-00029-of-00035.safetensors 5.4 GBmodel-00031-of-00035.safetensors 5.4 GBmodel-00005-of-00035.safetensors 5.4 GBmodel-00022-of-00035.safetensors 5.4 GBmodel-00004-of-00035.safetensors 5.4 GBmodel-00007-of-00035.safetensors 5.4 GBmodel-00001-of-00035.safetensors 5.0 GBmodel-00035-of-00035.safetensors 1.2 GBinternlm/Sage-S2.1-Flash