qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 19, 2026 · Apple M4
deepseek-r1:latest
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
82 vs 22
Hardware Fit
71 vs 69
Quality Score
86 vs 2
Hardware
qwen3:14b deepseek-r1:latest
MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM24 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:14b deepseek-r1:latest
Tokens/sec10.39.6
First chunk513 ms1300 ms
TTFT513 ms1.3 s
Load time7.2 s19.9 s
Memory usage9.4 GB4.8 GB
Memory %39%65%
HW Fit Score Breakdown
qwen3:14b
Speed
23/50
TTFT
20/20
Memory
28/30
deepseek-r1:latest
Speed
31/50
TTFT
20/20
Memory
18/30
Quality
qwen3:14b
Reasoning
17/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
deepseek-r1:latest
Reasoning
0/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
1/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor 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