gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jun 25, 2026 · Cortex-X925
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Aug 23, 2026 · Apple M1 Pro
Global Score
92 vs 69
Hardware Fit
86 vs 86
Quality Score
95 vs 62
Hardware
gpt-oss:20b qwen3.5:4b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
gpt-oss:20b qwen3.5:4b
Tokens/sec60.736.7
First chunk542 ms207 ms
TTFT3.2 s6.6 s
Load time12.0 s3.0 s
Memory usage12.0 GB5.3 GB
Memory %10%33%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
6/20
Memory
30/30
qwen3.5:4b
Speed
50/50
TTFT
7/20
Memory
29/30
Quality
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
qwen3.5:4b
Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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