ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
Global Score
72 vs 63
Hardware Fit
71 vs 100
Quality Score
72 vs 47
Hardware
ministral-3:8b llama3.2:1b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M1 ProCortex-A78AE
Cores106
RAM16 GB7 GB
GPUApple M1 ProIntegrated / Unknown
OSmacOS 26.6.2Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
ministral-3:8b llama3.2:1b
Tokens/sec19.840.2
First chunk269 ms1087 ms
TTFT269 ms1.1 s
Load time10.7 s6.2 s
Memory usage13.7 GB1.4 GB
Memory %86%19%
HW Fit Score Breakdown
ministral-3:8b
Speed
44/50
TTFT
20/20
Memory
7/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
llama3.2:1b
Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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