phi3:14b
OLLAMA GGUFphi3 · 14.0B · Q4_0
Mar 2, 2026 · Apple M4
deepseek-coder-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
63 vs 82
Hardware Fit
83 vs 100
Quality Score
55 vs 74
Hardware
phi3:14b deepseek-coder-v2:…
MachineMacBook AirNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
phi3:14b deepseek-coder-v2:…
Tokens/sec12.7117.2
First chunkN/A275 ms
TTFT434 ms275 ms
Load time0.9 s8.9 s
Memory usage17.7 GB17.9 GB
Memory %55%15%
HW Fit Score Breakdown
phi3:14b
Speed
23/50
TTFT
30/20
Memory
30/30
deepseek-coder-v2:16b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
phi3:14b
Reasoning
14/20
Coding
2/20
Instruction
14/20
Structured
7/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Strong
deepseek-coder-v2:16b
Reasoning
8/20
Coding
19/20
Instruction
13/20
Structured
12/15
Math
14/15
Multilingual
8/10
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