← back to catalog · registered 2026-09-04 22:03

mradermacher/KAT-Coder-V2.5-Dev-35B-A3B-MTP-ABLITERATED-GGUF

mradermacher 35B MoE 262K ctx
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/mradermacher%2FKAT-Coder-V2.5-Dev-35B-A3B-MTP-ABLITERATED-GGUF"
Response includes
  • classification m1
  • files 3
  • hub_downloads_all_time 2,539
  • author_summary 3358 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
3K
583 last 30d - stable
Likes
1
Model age
6w ago
created 2026-09-04
Downloads over time
Now2.9K→from0↑0%
01.1K2.1K3.2K0 on Sep 42.9K on Oct 20SepOct
Sep 4 → Oct 20 · 47 snapshots · spans 46 days

Variants by this author 2 formats · 4K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Quantizations
Q4_K
Tags
transformers gguf qwen3_5_moe kat-coder kat-coder-v2.5 qwen3.5 mixture-of-experts coding mtp speculative-decoding abliteration uncensored

Related

Total size
19.0 GB
Files
3
Quantizations
2
Registered
2026-09-04 22:03
Last updated on HF
2026-09-05 08:43

Files by quantization

Q4_K 1 file 19.0 GB
KAT-Coder-V2.5-Dev-35B-A3B-MTP-ABLITERATED.Q4_K_S.gguf 19.0 GB 29cbd995 download
Auxiliary files 2 files 1.96 KB
.gitattributes 1.57 KB d24c85ad download
README.md 395 B bc549071 download

README current version from Hugging Face

README history 11 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-09-05auto-patch README.md26b20f14.1 KB
    Loading...
  2. 2026-09-05auto-patch README.mda7b399f4.2 KB
    Loading...
  3. 2026-09-05auto-patch README.md1dcfe3e4.1 KB
    Loading...
  4. 2026-09-05auto-patch README.md353893a3.9 KB
    Loading...
  5. 2026-09-05auto-patch README.md65197db3.7 KB
    Loading...
  6. 2026-09-05auto-patch README.md3b2ffd03.3 KB
    Loading...
  7. 2026-09-05auto-patch README.mdeb43eb53.1 KB
    Loading...
  8. 2026-09-05auto-patch README.md23a86e92.8 KB
    Loading...
  9. 2026-09-04auto-patch README.mdc172c012.6 KB
    Loading...
  10. 2026-09-04auto-patch README.md85933d72.4 KB
    Loading...
  11. 2026-09-04uploaded from rich1f85e847395 B
    Loading...
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