gemma3:12b
OLLAMA GGUFgemma3 · 12.2B · Q4_K_M
Mar 2, 2026 · Apple M4
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
80 vs 68
Hardware Fit
83 vs 59
Quality Score
78 vs 72
Hardware
gemma3:12b qwen2.5-coder:7b
MachineMacBook AirASUS
CPUApple M4Intel Gen Intel® Core™ i7-13700K
Cores1024
RAM32 GB64 GB
GPUApple M4NVIDIA GeForce RTX 3070
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
gemma3:12b qwen2.5-coder:7b
Tokens/sec12.734.4
First chunkN/A1991 ms
TTFT560 ms2.0 s
Load time2.8 s40.6 s
Memory usage11.0 GB5.0 GB
Memory %34%8%
HW Fit Score Breakdown
gemma3:12b
Speed
23/50
TTFT
30/20
Memory
30/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
Quality
gemma3:12b
Reasoning
14/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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