phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Oct 20, 2026 · Apple M1 Pro
Global Score
64 vs 83
Hardware Fit
100 vs 75
Quality Score
48 vs 87
Hardware
phi3:3.8b openai/gpt-oss-20b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
phi3:3.8b openai/gpt-oss-20b
Tokens/sec42.043.2
First chunkN/A46 ms
TTFT142 ms30.0 s
Load time1.1 sN/A
Memory usage16.0 GB15.8 GB
Memory %50%49%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
25/30
Quality
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
openai/gpt-oss-20b
Reasoning
19/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong 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