qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
qwen3.8:latest
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
58 vs 68
Hardware Fit
82 vs 22
Quality Score
48 vs 88
Hardware
qwen3:14b qwen3.8:latest
MachineMacBook ProSystem manufacturer
CPUApple M1 MaxAMD Ryzen 9 5950X 16-Core Processor
Cores1032
RAM32 GB32 GB
GPUApple M1 MaxNVIDIA GeForce RTX 3090
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3:14b qwen3.8:latest
Tokens/sec24.410.0
First chunk294 ms1041 ms
TTFT7.9 s14.3 s
Load time3.7 s22.3 s
Memory usage13.8 GB26.2 GB
Memory %43%82%
HW Fit Score Breakdown
qwen3:14b
Speed
47/50
TTFT
5/20
Memory
30/30
qwen3.8:latest
Speed
12/50
TTFT
1/20
Memory
9/30
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
qwen3.8:latest
Reasoning
19/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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