qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Apple M4
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
Global Score
48 vs 83
Hardware Fit
77 vs 65
Quality Score
35 vs 90
Hardware
qwen3.5:4b gpt-oss:20b
MachineMac miniMac mini
CPUApple M4Apple M4
Cores1010
RAM16 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:4b gpt-oss:20b
Tokens/sec18.917.1
First chunk316 ms705 ms
TTFT13.0 s10.2 s
Load time3.7 s23.1 s
Memory usage5.9 GB13.1 GB
Memory %37%55%
HW Fit Score Breakdown
qwen3.5:4b
Speed
43/50
TTFT
4/20
Memory
30/30
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
Quality
qwen3.5:4b
Reasoning
10/20
Coding
1/20
Instruction
4/20
Structured
3/15
Math
8/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
18/20
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