qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
34 vs 88
Hardware Fit
58 vs 86
Quality Score
23 vs 89
Hardware
qwen3.5:latest gemma4:12b-it-qat
MachineMac miniMac mini
CPUApple M4Apple M4 Pro
Cores1012
RAM16 GB24 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:latest gemma4:12b-it-qat
Tokens/sec13.330.0
First chunk438 ms686 ms
TTFT19.8 s7.1 s
Load time0.2 s5.4 s
Memory usage8.0 GB7.1 GB
Memory %50%30%
HW Fit Score Breakdown
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
qwen3.5:latest
Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak 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