jarrelscy/MiMo-V2.6-Pro-EXL3
text-generation model by jarrelscy
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Experimental sequential quantization checkpoint. Not a ready-to-serve model. Completed full-corpus joint-PV layers: [1, 2]. Each completed layer's run traversed all 18,006,461 training tokens. Validation alone selects the retained checkpoint, which may precede the end of the corpus pass or retain the initial fit when it is better. The selected step and corpus coverage are recorded in reports. Cold experts use mixed-rate EXL3 trellis codes at <=2 actual packed bits per weight. Initial trellis fitting uses a calibration subset; subsequent full-corpus PV jointly optimizes all input/output scales against the combined routed layer output while holding trellis codes fixed. No neurons are removed. The exact original 1,325 hot experts (5.00075% globally) retain their NVFP4 weights and assignment; this is not a separate 5% allocation per layer. Later layers use inputs propagated through earlier accepted EXL3 layers. Validation and audit each use 16,384 held-out tokens. reports/layererrors.csv records EXL3 validation and audit reconstruction errors.…
Read the full model card ↗ · Preview checked 2026-09-24T07:42:33.515Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
jarrelscy/MiMo-V2.6-Pro-EXL3 is a text-generation model repository published by jarrelscy on Hugging Face. The source reports the custom library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- custom
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-09-24T06:05:21.000Z
- Last modified
- 2026-09-24T06:23:56.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: XiaomiMiMo/MiMo-V2.6-Pro-RL
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-24T06:37:32.927Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF