Hollow markers & dashed spokes: axis not yet scored
G
82.5
A
97.5
U
—
N
—
T
93.1
L
—
E
99
T
25.2
Specification
- Parameters
- 27B
- Architecture
- qwen3_5
- Size on disk
- 7.9 GB
- Quantization
- 2bit (ternary, PrismML extreme compression)
- Format
- MLX
- Reasoning (CoT)
- Yes — emits reasoning tokens
- Internal ID
- M21
- Mean speed
- 41.1 tok/s across suites
- Stall census
- 2 stalls in 29 observed tests (6.9%)
- Reasoning appetite
- 2,960 tokens mean · 15,892 max
- Model card
- lmstudio.ai
Suite results
| Suite | Score | Avg / 20 | Tests | tok/s |
|---|---|---|---|---|
| General capability (13-task real-workload suite) 1a | 214.5 / 260 | 16.5 | 13/13 | 40.7 |
| Agentic tool-calling & protocol adherence 1b | 156 / 160 | 19.5 | 8/8 | 48.9 |
| Coding depth 1c | 118.8 / 120 | 19.8 | 6/6 | 33.8 |
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.