qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
89 vs 84
Hardware Fit
97 vs 82
Quality Score
86 vs 85
Hardware
qwen/qwen3.6-35b-a3b gemma4:12b-mlx
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M2 Pro
Cores1810
RAM64 GB16 GB
GPUApple M5 MaxApple M2 Pro
OSmacOS 27.0macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.6-35b-a3b gemma4:12b-mlx
Tokens/sec130.227.2
First chunk5 ms732 ms
TTFT135 ms8.1 s
Load timeN/A3.5 s
Memory usage26.6 GB7.1 GB
Memory %42%44%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
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
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest