ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Jun 25, 2026 · Apple M4 Pro
qwen2.5-coder:32b
OLLAMA GGUFqwen2 · 32.8B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
79 vs 78
Hardware Fit
98 vs 59
Quality Score
71 vs 86
Hardware
ministral-3:8b qwen2.5-coder:32b
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1220
RAM24 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.6.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
ministral-3:8b qwen2.5-coder:32b
Tokens/sec41.49.5
First chunk257 ms394 ms
TTFT257 ms395 ms
Load time5.2 s72.1 s
Memory usage9.0 GB26.5 GB
Memory %38%22%
HW Fit Score Breakdown
ministral-3:8b
Speed
50/50
TTFT
20/20
Memory
28/30
qwen2.5-coder:32b
Speed
9/50
TTFT
20/20
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
qwen2.5-coder:32b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong 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