qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 2, 2026 · Apple M4
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
May 25, 2026 · Apple M4 Pro
Global Score
47 vs 94
Hardware Fit
67 vs 92
Quality Score
38 vs 95
Hardware
qwen3:8b gpt-oss:20b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M4 Pro
Cores1014
RAM32 GB48 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:8b gpt-oss:20b
Tokens/sec18.754.5
First chunkN/A318 ms
TTFT12.1 s2.9 s
Load time1.2 s4.0 s
Memory usage9.5 GB16.4 GB
Memory %30%34%
HW Fit Score Breakdown
qwen3:8b
Speed
31/50
TTFT
6/20
Memory
30/30
gpt-oss:20b
Speed
50/50
TTFT
13/20
Memory
29/30
Quality
qwen3:8b
Reasoning
5/20
Coding
5/20
Instruction
4/20
Structured
12/15
Math
2/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Poor Structured Output: Strong Math: Poor Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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