ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Jun 25, 2026 · Apple M4 Pro
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-6500
Global Score
79 vs 61
Hardware Fit
98 vs 69
Quality Score
71 vs 58
Hardware
ministral-3:8b qwen3.5:4b
MachineMac miniGigabyte Technology Co., Ltd. H170M-D3H
CPUApple M4 ProIntel Core™ i5-6500
Cores124
RAM24 GB16 GB
GPUApple M4 ProGP104 [GeForce GTX 1070]
OSmacOS 15.6.1Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
ministral-3:8b qwen3.5:4b
Tokens/sec41.435.7
First chunk257 ms438 ms
TTFT257 ms5.1 s
Load time5.2 s40.1 s
Memory usage9.0 GB5.5 GB
Memory %38%35%
HW Fit Score Breakdown
ministral-3:8b
Speed
50/50
TTFT
20/20
Memory
28/30
qwen3.5:4b
Speed
50/50
TTFT
11/20
Memory
8/30
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
qwen3.5:4b
Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate 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