Alkus 2.6 is a reasoning model — a coding-, cybersecurity-, 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. It thinks in explicit chain-of-thought and has found real, previously-unknown vulnerabilities in production code.
<think> chain-of-thought, verification-forward, with tool use| 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) |
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.
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."
Inherits the license of the Qwen base model.
Qwen/Qwen3.8-27B