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

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
95 vs 80
Hardware Fit
94 vs 77
Quality Score
96 vs 81

Hardware

qwen3-30b-a3b-thin… qwen3.6:35b-mlx
MachineMac StudioMacBook Pro
CPUApple M2 MaxApple M5 Max
Cores1218
RAM96 GB48 GB
GPUApple M2 MaxApple M5 Max
OSmacOS 26.1macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… qwen3.6:35b-mlx
Tokens/sec80.4129.8
First chunk46 ms77 ms
TTFT1.8 s30.0 s
Load timeN/A1.8 s
Memory usage21.2 GB19.7 GB
Memory %22%41%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

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

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong
View qwen3-30b-a3b-thin… details | View qwen3.6:35b-mlx 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