Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

gemma4:12b-mlx

OLLAMA GGUF
Not Rec.

Aug 24, 2026 · Apple M1 Pro

Global Score
84 vs 71
Hardware Fit
78 vs 76
Quality Score
86 vs 69

Hardware

qwen/qwen3.6-35b-a3b gemma4:12b-mlx
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M1 ProApple M1 Pro
OSmacOS 15.6.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.6-35b-a3b gemma4:12b-mlx
Tokens/sec49.925.0
First chunk31 ms787 ms
TTFT708 ms30.0 s
Load timeN/A4.0 s
Memory usage26.6 GB7.1 GB
Memory %83%45%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
8/30

gemma4:12b-mlx

Speed
50/50
TTFT
0/20
Memory
26/30

Quality

qwen/qwen3.6-35b-a3b

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma4:12b-mlx

Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen/qwen3.6-35b-a3b details | View gemma4:12b-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