← Leaderboard

DeepSeek-R1-Distill-Qwen-32B 8bit MLX

Retired Rank #29 of 33 · 2/8 GAUNTLET progress
Generalist — 60.5 / 100 G Agentic — pending A Understanding — pending U Needle — pending N Thinking — pending T Live — pending L Engineering — pending E Throughput — 8 / 100 T

Hollow markers & dashed spokes: axis not yet scored

G
60.5
A
U
N
T
n/d
L
E
T
8

Specification

Parameters
32B
Architecture
qwen2
Size on disk
34.82 GB
Quantization
8bit
Format
MLX
Reasoning (CoT)
Yes — emits reasoning tokens
Internal ID
M12
Mean speed
13.1 tok/s across suites
Stall census
1 stall in 13 observed tests (7.7%)
Reasoning appetite
1,057 tokens mean · 7,789 max

Suite results

Suite Score Avg / 20 Tests tok/s
General capability (13-task real-workload suite) 1a 157.3 / 260 12.1 13/13 13.1

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.