qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 19, 2026 · Apple M4
deepseek-coder-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
82 vs 83
Hardware Fit
71 vs 100
Quality Score
86 vs 75
Hardware
qwen3:14b deepseek-coder-v2:…
MachineMac miniGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M4Intel Core™ i5-14400F
Cores1016
RAM24 GB32 GB
GPUApple M4NVIDIA GeForce RTX 5060 Ti
OSmacOS 26.3Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3:14b deepseek-coder-v2:…
Tokens/sec10.3150.4
First chunk513 ms116 ms
TTFT513 ms116 ms
Load time7.2 s5.8 s
Memory usage9.4 GB9.4 GB
Memory %39%30%
HW Fit Score Breakdown
qwen3:14b
Speed
23/50
TTFT
20/20
Memory
28/30
deepseek-coder-v2:16b
Speed
50/50
TTFT
20/20
Memory
30/30
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-coder-v2:16b
Reasoning
10/20
Coding
18/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
9/10
Reasoning: Weak 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