← back to catalog · registered 2026-11-21 12:04

TheShellMaster/cypher-Devstral-Small-2-24B-abliterated

TheShellMaster 24B GGUF multimodal second-order
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/TheShellMaster%2Fcypher-Devstral-Small-2-24B-abliterated"
Response includes
  • classification m8
  • files 4
  • author_summary 15 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
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 2026-11-21
Downloads over time
Now 0 → from 0 ↑ 0%
0011 0 on Nov 21 0 on Nov 22 Nov
Nov 21 → Nov 22 · 2 snapshots · spans 1 day

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Quantizations
Q5_K
Tags
gguf devstral mistral3 vision abliterated tool-calling cypher-studio base_model:mradermacher/Huihui-Devstral-Small-2-24B-Instruct-2512-abliterated-i1-GGUF base_model:quantized:mradermacher/Huihui-Devstral-Small-2-24B-Instruct-2512-abliterated-i1-GGUF license:apache-2.0 endpoints_compatible region:us

Related

Total size
15.6 GB
Files
4
Quantizations
3
Registered
2026-11-21 12:04
Last updated on HF
2026-11-21 11:38

Files by quantization

Q5_K 1 file 15.6 GB
Huihui-Devstral-Small-2-24B-Instruct-2512-abliterated.i1-Q5_K_M.gguf 15.6 GB 108e7fce download
F16 1 file 837 MB
Huihui-Devstral-Small-2-24B-Instruct-2512-abliterated.mmproj-f16.gguf 837 MB a192eab9 download
Auxiliary files 2 files 2.44 KB
.gitattributes 1.69 KB 2c8254d5 download
README.md 772 B 89e80c64 download

README current version from Hugging Face


license: apache-2.0
tags:

  • gguf
  • devstral
  • mistral3
  • vision
  • abliterated
  • tool-calling
  • cypher-studio
    base_model: mradermacher/Huihui-Devstral-Small-2-24B-Instruct-2512-abliterated-i1-GGUF

Cypher Devstral-Small-2 24B Abliterated (i1-Q5_K_M GGUF + Vision)

Miroir souverain Cypher Studio (cypher-opencode) optimise pour Kaggle Dual-T4 (30 Go VRAM) sous llama-server --jinja.

  • Architecture : Dense 24B Ministral 3 specialise agent CLI/code, sans latence <think>
  • Quantification : i1-Q5_K_M imatrix (15.61 GiB) + mmproj-f16 (vision native)
  • Capacites : Tool Calling natif Mistral, Vision multimodale, contexte 64K-256K
  • Source amont : mradermacher/Huihui-Devstral-Small-2-24B-Instruct-2512-abliterated-i1-GGUF
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