qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
microllm-250m:latest
OLLAMA GGUFllama · 256.74M · F16
Jul 5, 2026 · Apple M4 Pro
Global Score
58 vs 34
Hardware Fit
82 vs 100
Quality Score
48 vs 6
Hardware
qwen3:14b microllm-250m:latest
MachineMacBook ProMac mini
CPUApple M1 MaxApple M4 Pro
Cores1012
RAM32 GB24 GB
GPUApple M1 MaxApple M4 Pro
OSmacOS 26.3macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:14b microllm-250m:latest
Tokens/sec24.4291.6
First chunk294 ms50 ms
TTFT7.9 s79 ms
Load time3.7 s0.0 s
Memory usage13.8 GB0.6 GB
Memory %43%2%
HW Fit Score Breakdown
qwen3:14b
Speed
47/50
TTFT
5/20
Memory
30/30
microllm-250m:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3:14b
Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
microllm-250m:latest
Reasoning
1/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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