Back to leaderboard

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 22, 2026 · Apple M2 Max

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Jul 31, 2026 · Intel Xeon® E5-2637 v3

Global Score
95 vs 81
Hardware Fit
94 vs 72
Quality Score
96 vs 85

Hardware

qwen3-30b-a3b-thin… qwen3.5:35b-a3b-q4…
MachineMac StudioDell Inc. Precision Tower 7910
CPUApple M2 MaxIntel Xeon® E5-2637 v3
Cores1216
RAM96 GB96 GB
GPUApple M2 MaxNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.1Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… qwen3.5:35b-a3b-q4…
Tokens/sec80.424.2
First chunk46 ms1607 ms
TTFT1.8 s1.6 s
Load timeN/A66.4 s
Memory usage21.2 GB22.7 GB
Memory %22%24%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
14/20
Memory
30/30

qwen3.5:35b-a3b-q4_K_M

Speed
28/50
TTFT
14/20
Memory
30/30

Quality

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:35b-a3b-q4_K_M

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-30b-a3b-thin… details | View qwen3.5:35b-a3b-q4… details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest