benthecarman/MiMo-V2.6-Flash-MOPD-exl3
text-generation model by benthecarman
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.
XiaomiMiMo/MiMo-V2.6-Flash-MOPD (309B total / 15B active MoE) quantized to EXL3 at 2.27 bpw, so it fits on a single 128 GB machine such as an NVIDIA DGX Spark. MOPD is Xiaomi's update to MiMo-V2.6-Flash-RL. It mainly fixes tool-call repetition in agentic use: the model issuing the same tool calls over and over without making progress. The quant of the earlier checkpoint is benthecarman/MiMo-V2.6-Flash-RL-exl3. The repo includes the vision tower, the MTP heads, and Xiaomi's DFlash speculative-decoding drafter, fixed so it loads and quantized to 4 bpw. Requires exllamav3 v1.5.2 or later; see How to run. Converted with exllamav3 v1.5.2, convert.py -b 2.25 -hq -cr 250 -cc 2048. The per-module result: This is the same allocation as the Flash-RL quant, so the two are directly comparable. Layer 47: some of its experts produce intermediate values past the fp16 limit. exllamav3 scales upproj down by 128 in that layer (intermdiv) and restores…
Read the full model card ↗ · Preview checked 2026-09-28T07:17:59.520Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
benthecarman/MiMo-V2.6-Flash-MOPD-exl3 is a text-generation model repository published by benthecarman on Hugging Face. A library was not reported.
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
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 45,777,830,784
- Architecture
- MiMoV2ForCausalLM
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2026-09-28T05:59:33.000Z
- Last modified
- 2026-09-28T06:01:41.000Z
Compatibility and lineage
Reported languages: en, zh
Reported base models: XiaomiMiMo/MiMo-V2.6-Flash-MOPD
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 2026-09-28T06:38:00.545Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5