← Leaderboard
Qwen3.6-27B Fable-Fusion-711 Uncensored Heretic NEO-MAX Q8_0 GGUF
Keeper Rank #7 of 33 · 6/8 GAUNTLET progress
Hollow markers & dashed spokes: axis not yet scored
G
89
A
99.5
U
—
N
90.5
T
97.7
L
—
E
89
T
6.7
Specification
- Parameters
- 27B
- Architecture
- qwen3.6 hybrid Gated DeltaNet/Attention (same base architecture as M7)
- Size on disk
- 29.79 GB
- Quantization
- Q8_0
- Format
- GGUF
- Reasoning (CoT)
- Yes — emits reasoning tokens
- Internal ID
- M15
- Mean speed
- 11 tok/s across suites
- Stall census
- 1 stall in 43 observed tests (2.3%)
- Reasoning appetite
- 2,046 tokens mean · 16,383 max
- Model card
- huggingface.co
Suite results
| Suite | Score | Avg / 20 | Tests | tok/s |
|---|---|---|---|---|
| General capability (13-task real-workload suite) 1a | 231.4 / 260 | 17.8 | 13/13 | 12.8 |
| Agentic tool-calling & protocol adherence 1b | 159.2 / 160 | 19.9 | 8/8 | 12.4 |
| Coding depth 1c | 106.8 / 120 | 17.8 | 6/6 | 14 |
| Content-production depth 1e | 118.8 / 120 | 19.8 | 6/6 | 15.2 |
| Long-context retrieval & synthesis 1g | 118.8 / 120 | 19.8 | 6/6 | 7 |
| Long-context multi-needle (MRCR) 1g2 | 44.1 / 60 | 14.7 | 3/3 | 4.5 |
Each test is LLM-judged 0–20 against a fixed rubric; suite max = tests × 20. Where fewer tests ran than the suite total, unrun tests count as zero toward the axis score. See methodology.