ministral-3:3b
OLLAMA GGUFmistral3 · 3.8B · Q4_K_M
Mar 6, 2026 · Apple M4
gemma3:4b
OLLAMA GGUFgemma3 · 4.3B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
71 vs 76
Hardware Fit
99 vs 92
Quality Score
59 vs 69
Hardware
ministral-3:3b gemma3:4b
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
ministral-3:3b gemma3:4b
Tokens/sec42.215.0
First chunk189 ms2380 ms
TTFT189 ms2.4 s
Load time1.2 s13.6 s
Memory usage7.0 GB2.6 GB
Memory %22%35%
HW Fit Score Breakdown
ministral-3:3b
Speed
50/50
TTFT
20/20
Memory
29/30
gemma3:4b
Speed
45/50
TTFT
18/20
Memory
29/30
Quality
ministral-3:3b
Reasoning
5/20
Coding
16/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
gemma3:4b
Reasoning
11/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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