qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
89 vs 88
Hardware Fit
97 vs 86
Quality Score
86 vs 89
Hardware
qwen/qwen3.6-35b-a3b gemma4:12b-it-qat
MachineMacBook ProMac mini
CPUApple M5 MaxApple M4 Pro
Cores1812
RAM64 GB24 GB
GPUApple M5 MaxApple M4 Pro
OSmacOS 27.0macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.6-35b-a3b gemma4:12b-it-qat
Tokens/sec130.230.0
First chunk5 ms686 ms
TTFT135 ms7.1 s
Load timeN/A5.4 s
Memory usage26.6 GB7.1 GB
Memory %42%30%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
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-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
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