gemma3:12b
OLLAMA GGUFgemma3 · 12.2B · Q4_K_M
Mar 2, 2026 · Apple M4
mistral:latest
OLLAMA GGUFllama · 7.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
Global Score
80 vs 73
Hardware Fit
83 vs 100
Quality Score
78 vs 62
Hardware
gemma3:12b mistral:latest
MachineMacBook AirMicro-Star International Co., Ltd. MS-7B79
CPUApple M4AMD Ryzen 5 2600X Six-Core Processor
Cores1012
RAM32 GB16 GB
GPUApple M4NVIDIA GeForce GTX 1080
OSmacOS 26.3Microsoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma3:12b mistral:latest
Tokens/sec12.731.7
First chunkN/A102 ms
TTFT560 ms102 ms
Load time2.8 s14.3 s
Memory usage11.0 GB4.8 GB
Memory %34%30%
HW Fit Score Breakdown
gemma3:12b
Speed
23/50
TTFT
30/20
Memory
30/30
mistral:latest
Speed
50/50
TTFT
20/20
Memory
30/30
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
mistral:latest
Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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