phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
Global Score
64 vs 88
Hardware Fit
100 vs 80
Quality Score
48 vs 91
Hardware
phi3:3.8b gpt-oss-orchestrat…
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
phi3:3.8b gpt-oss-orchestrat…
Tokens/sec42.024.6
First chunkN/A525 ms
TTFT142 ms4.8 s
Load time1.1 s8.5 s
Memory usage16.0 GB13.8 GB
Memory %50%58%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
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
gpt-oss-orchestrator:la…
Reasoning
19/20
Coding
19/20
Instruction
13/20
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