deepseek-r1:14b
OLLAMA GGUFqwen2 · 14.8B · Q4_K_M
Mar 2, 2026 · Apple M4
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
22 vs 72
Hardware Fit
50 vs 71
Quality Score
10 vs 72
Hardware
deepseek-r1:14b ministral-3:8b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
deepseek-r1:14b ministral-3:8b
Tokens/sec11.419.8
First chunkN/A269 ms
TTFT30.0 s269 ms
Load time1.0 s10.7 s
Memory usage16.5 GB13.7 GB
Memory %52%86%
HW Fit Score Breakdown
deepseek-r1:14b
Speed
20/50
TTFT
0/20
Memory
30/30
ministral-3:8b
Speed
44/50
TTFT
20/20
Memory
7/30
Quality
deepseek-r1:14b
Reasoning
1/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate
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
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