Muse-Spark-Open-816B-A42B-oQ4e
This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with oQe importance-matrix quantization.
A mixed-precision MLX checkpoint of meta-models/Muse-Spark-Open-816B-A42B, Meta's 816B total / 42B active Mixture-of-Experts model with a 1M-token context window, built for coding and agentic work. It includes the language model and the vision encoder. The audio encoder is not included.
The routed experts of layers 1-60 are passed through unchanged from the official NVFP4 release (meta-models/Muse-Spark-Open-816B-A42B-NVFP4), with their per-expert tensor scales.
The effective average is 4.632 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
oQ4e allocates bits by measured layer sensitivity, then rounds each affine group with an importance matrix (128 samples x 512 tokens) and a weighted least-squares refit of its scale and bias. The NVFP4 experts pass through unchanged.
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| NVFP4, group 16 | 773.094B | 94.060% | 405.000 GiB | 4.50 |
| Affine 4-bit, group 64 | 25.770B | 3.135% | 13.500 GiB | 4.50 |
| Affine 8-bit, group 64 | 20.557B | 2.501% | 20.342 GiB | 8.50 |
| Affine 5-bit, group 64 | 0.436B | 0.053% | 0.279 GiB | 5.50 |
| BF16 | 1.931B | 0.235% | 3.597 GiB | 16.00 |
| FP32 | 0.130B | 0.016% | 0.484 GiB | 32.00 |
| Total | 821.919B | 100% | 443.203 GiB | 4.632 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language backbone | 819.991B | 472.029 GB / 439.612 GiB |
| Vision encoder | 1.928B | 3.856 GB / 3.591 GiB |
| Total | 821.919B | 475.886 GB / 443.203 GiB |
[!WARNING] This checkpoint takes about 476 GB, which is more than a single 512 GB Mac can run reliably. For one 512 GB Mac, use the oQ3e quant instead.
Use with oMLX
Download the model in oMLX and chat with it in the built-in chat UI. You can add images and set the reasoning effort from low to xhigh. Reasoning cannot be turned off, and the default (Auto) uses xhigh.
You can also use
- mlx-community/Muse-Spark-Open-816B-A42B-oQ3e: the 3-bit oQ quant.
- mlx-community/Muse-Spark-Open-816B-A42B-3bit: the standard mlx-lm 3-bit quant.
- mlx-community/Muse-Spark-Open-816B-A42B-4bit: the standard mlx-lm 4-bit quant.
License
Muse Model License, following the source model. See LICENSE.md and USE_POLICY.md.