ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Jun 25, 2026 · Apple M4 Pro
gemma4:26b
OLLAMA GGUFgemma4 · 25.2B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
79 vs 84
Hardware Fit
98 vs 80
Quality Score
71 vs 86
Hardware
ministral-3:8b gemma4:26b
MachineMac miniSystem manufacturer
CPUApple M4 ProAMD Ryzen 9 5950X 16-Core Processor
Cores1232
RAM24 GB32 GB
GPUApple M4 ProNVIDIA GeForce RTX 3090
OSmacOS 15.6.1Microsoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced
Performance
ministral-3:8b gemma4:26b
Tokens/sec41.4147.6
First chunk257 ms139 ms
TTFT257 ms30.0 s
Load time5.2 s21.3 s
Memory usage9.0 GB1.7 GB
Memory %38%5%
HW Fit Score Breakdown
ministral-3:8b
Speed
50/50
TTFT
20/20
Memory
28/30
gemma4:26b
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
gemma4:26b
Reasoning
17/20
Coding
14/20
Instruction
18/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong 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