← Leaderboard

Qwen3.6-35B-A3B MLX 8bit Uniform (lmstudio-community)

Retired Rank #21 of 33 · 2/8 GAUNTLET progress
Generalist — 85.5 / 100 G Agentic — pending A Understanding — pending U Needle — pending N Thinking — pending T Live — pending L Engineering — pending E Throughput — 53.6 / 100 T

Hollow markers & dashed spokes: axis not yet scored

G
85.5
A
U
N
T
n/d
L
E
T
53.6

Specification

Parameters
35B total / 3B active per token
Architecture
qwen3_5_moe
Size on disk
37.75 GB
Quantization
8bit uniform
Format
MLX
Reasoning (CoT)
Yes — emits reasoning tokens
Internal ID
M9
Mean speed
87.5 tok/s across suites
Stall census
1 stall in 13 observed tests (7.7%)
Reasoning appetite
3,254 tokens mean · 7,730 max
Model card
lmstudio.ai

Suite results

Suite Score Avg / 20 Tests tok/s
General capability (13-task real-workload suite) 1a 222.3 / 260 17.1 13/13 87.5

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.