← back to catalog · registered 2026-11-11 14:03

MK4-Research/Alkus-2.6-27B-Abliterated-GGUF

MK4-Research Qwen 27B GGUF
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/MK4-Research%2FAlkus-2.6-27B-Abliterated-GGUF"
Response includes
  • classification m8
  • files 3
  • author_summary 3 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
303
Likes
2
Model age
1w ago
created 2026-11-11
Downloads over time
Now 303 → from 0 ↑ 0%
0111222333 0 on Nov 11 303 on Nov 22 Nov
Nov 11 → Nov 22 · 12 snapshots · spans 11 days

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
Q4_K
Tags
gguf safetensors qwen3 coding reasoning cybersecurity security vulnerability-detection code-analysis abliterated llama.cpp text-generation

Related

Control vectors

Total size
15.4 GB
Files
3
Quantizations
2
Registered
2026-11-11 14:03
Last updated on HF
2026-11-11 18:39

Files by quantization

Q4_K 1 file 15.4 GB
Alkus-2.6-27B-Abliterated-Q4_K_M.gguf 15.4 GB c08c8871 download
Auxiliary files 2 files 3.59 KB
README.md 2.04 KB 0dc2199e download
.gitattributes 1.56 KB 45edce72 download

README current version from Hugging Face


license: apache-2.0
base_model: Qwen/Qwen3.8-27B
library_name: gguf
tags:

  • gguf
  • qwen3
  • coding
  • reasoning
  • abliterated
  • llama.cpp
    pipeline_tag: text-generation

Alkus 2.6 27B (Abliterated) - GGUF

Alkus 2.6 is a coding- and persistence-focused fine-tune of Qwen3.8-27B (abliterated base),
trained as a LoRA adapter on hand-written reasoning data and converted to GGUF for
llama.cpp / LM Studio.

  • Base: Qwen3.8-27B (abliterated)
  • Fine-tune: QLoRA, LoRA rank 16, 2 epochs on a single A100 (train_loss 0.968 / eval_loss 0.917)
  • Reasoning style: telegraphic, verification-forward chain-of-thought with explicit tool use
  • Note: the base is abliterated (reduced refusal behavior). Use responsibly and at your own risk.

Files

File Quant Size
Alkus-2.6-27B-Abliterated-Q4_K_M.gguf Q4_K_M ~15 GB
Alkus-2.6-27B-Abliterated-BF16.gguf BF16 ~50 GB (full precision)

Benchmarks

Evaluated with the EleutherAI lm-evaluation-harness (canonical few-shot, no chat template),
with the base loaded as NF4 4-bit plus the LoRA adapter.

Task Setting Metric Alkus 2.6
ARC-Easy 0-shot acc 84.0 (acc_norm 83.5)
PIQA 0-shot acc 81.0 (acc_norm 82.3)
WinoGrande 5-shot acc 77.3
ARC-Challenge 25-shot acc 69.3 (acc_norm 74.2)

PIQA is the clean apples-to-apples comparison (both 0-shot lm-eval): the published
Qwen3.8-27B base scores about 81.6, and Alkus 2.6 scores 81.0 - effectively a tie. The
coding- and persistence-oriented fine-tune did not degrade general-benchmark performance.

GSM8K and MMLU were not completed for this release.

Recommended runtime

  • Context: up to 131072
  • Flash Attention: on
  • K/V cache: Q8_0
  • Fits comfortably in 24 GB+ VRAM at Q4_K_M; BF16 is for full-precision use.

Usage (llama.cpp)

llama-cli -m Alkus-2.6-27B-Abliterated-Q4_K_M.gguf \
  -c 131072 -fa -ctk q8_0 -ctv q8_0 \
  -p "Write and test a Python function that merges overlapping intervals."

License

Inherits the license of the Qwen base model.

README history 8 versions

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

  1. 2026-11-11 Drop Apple attribution from text; keep capability claim dc309fd 2.6 KB
    Loading...
  2. 2026-11-11 Update README.md 79f36d4 2.6 KB
    Loading...
  3. 2026-11-11 Reasoning + cybersecurity framing, vuln-finding note, security tags ca0b83d 2.6 KB
    Loading...
  4. 2026-11-11 Update README.md 3eb9a6f 2.2 KB
    Loading...
  5. 2026-11-11 Update README.md 64ccd63 2.3 KB
    Loading...
  6. 2026-11-11 Update README.md fa54a3c 2.2 KB
    Loading...
  7. 2026-11-11 Embed benchmark chart in card b00f476 2.1 KB
    Loading...
  8. 2026-11-11 Add model card with benchmarks 944ba5e 2 KB
    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