gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
88 vs 68
Hardware Fit
86 vs 59
Quality Score
89 vs 72
Hardware
gemma4:12b-it-qat qwen2.5-coder:7b
MachineMac miniASUS
CPUApple M4 ProIntel Gen Intel® Core™ i7-13700K
Cores1224
RAM24 GB64 GB
GPUApple M4 ProNVIDIA GeForce RTX 3070
OSmacOS 15.6.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
gemma4:12b-it-qat qwen2.5-coder:7b
Tokens/sec30.034.4
First chunk686 ms1991 ms
TTFT7.1 s2.0 s
Load time5.4 s40.6 s
Memory usage7.1 GB5.0 GB
Memory %30%8%
HW Fit Score Breakdown
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
Quality
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
qwen2.5-coder:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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