← back to catalog · registered 2026-10-07 22:58

dotyerts/MiMo-V2.6-Flash-RL-UNCENSORED-oQ8e-mtp

Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/dotyerts%2FMiMo-V2.6-Flash-RL-UNCENSORED-oQ8e-mtp"
Response includes
  • classification unknown
  • files 44
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-10-07

Metadata

Tags
mlx safetensors mimo_v2 oq quantized custom_code 8-bit region:us
Total size
157 GB
Files
44
Quantizations
1
Registered
2026-10-07 22:58
Last updated on HF
2026-10-07 22:52

Files by quantization

Auxiliary files 44 files 157 GB
model-00002-of-00030.safetensors 5.56 GB 9fc186b4 download
model-00018-of-00030.safetensors 5.31 GB 80af48dd download
model-00016-of-00030.safetensors 5.31 GB e0afa002 download
model-00019-of-00030.safetensors 5.31 GB 7e889bfd download
model-00028-of-00030.safetensors 5.31 GB eca6587c download
model-00009-of-00030.safetensors 5.31 GB 9dbb0364 download
model-00011-of-00030.safetensors 5.31 GB 17af593a download
model-00015-of-00030.safetensors 5.31 GB 5723495d download
model-00017-of-00030.safetensors 5.31 GB 1fee09e3 download
model-00020-of-00030.safetensors 5.31 GB 39aec497 download
model-00021-of-00030.safetensors 5.31 GB d4a7f529 download
model-00012-of-00030.safetensors 5.31 GB 9dc4eb8a download
model-00024-of-00030.safetensors 5.31 GB 8eeac4a8 download
model-00027-of-00030.safetensors 5.31 GB 86eb5043 download
model-00013-of-00030.safetensors 5.31 GB c2a33664 download
model-00022-of-00030.safetensors 5.31 GB df8d6363 download
model-00008-of-00030.safetensors 5.31 GB c45e9ada download
model-00014-of-00030.safetensors 5.31 GB 07e8e2c2 download
model-00023-of-00030.safetensors 5.31 GB 00cfd441 download
model-00029-of-00030.safetensors 5.31 GB c0d0abbd download
model-00010-of-00030.safetensors 5.31 GB e69640d8 download
model-00025-of-00030.safetensors 5.31 GB 03c04015 download
model-00006-of-00030.safetensors 5.31 GB 04c65a4b download
model-00007-of-00030.safetensors 5.31 GB c709bbda download
model-00026-of-00030.safetensors 5.31 GB 811b95de download
model-00004-of-00030.safetensors 5.31 GB b356a834 download
model-00005-of-00030.safetensors 5.31 GB f9ee1b72 download
model-00003-of-00030.safetensors 5.31 GB e8232896 download
model-00001-of-00030.safetensors 4.66 GB 409ea371 download
model-00030-of-00030.safetensors 3.19 GB 65e76987 download
tokenizer.json 10.9 MB ff15eb92 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 20024bfe download
model.safetensors.index.json 98.6 KB 601f5e07 download
modeling_mimo_v2.py 83.5 KB 40225ab4 download
config.json 38.6 KB 554dc3aa download
oq_imatrix_report.json 15.7 KB 59fa28fc download
tokenizer_config.json 11.9 KB 39a944cb download
configuration_mimo_v2.py 9.81 KB bb6f4472 download
chat_template.jinja 4.03 KB 4199fa7b download
.gitattributes 1.53 KB 52373fe2 download
preprocessor_config.json 350 B f411f0c1 download
README.md 327 B 2f44b42c download
generation_config.json 195 B 167a2b07 download

README current version from Hugging Face


library_name: mlx
tags:

  • mlx
  • oq
  • quantized

MiMo-V2.6-Flash-RL-UNCENSORED-oQ8e-mtp

This model was quantized using oQ (oMLX v0.7.0) mixed-precision quantization.

Quantization details

  • Model type: mimo_v2
  • Bits: 8
  • Group size: 64
  • Format: MLX safetensors
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration