gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
76 vs 87
Hardware Fit
46 vs 81
Quality Score
89 vs 90
Hardware
gemma4:31b GPT-20B:20b
MachineMacBook ProHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUApple M4 MaxAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1632
RAM64 GB31 GB
GPUApple M4 MaxAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSmacOS 26.3.1Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:31b GPT-20B:20b
Tokens/sec22.436.9
First chunk565 ms902 ms
TTFT30.0 s4.2 s
Load time6.9 s19.5 s
Memory usage43.9 GB13.1 GB
Memory %69%42%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
GPT-20B:20b
Speed
47/50
TTFT
7/20
Memory
27/30
Quality
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
GPT-20B:20b
Reasoning
19/20
Coding
17/20
Instruction
14/20
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