Back to leaderboard

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

Global Score
86 vs 87
Hardware Fit
80 vs 81
Quality Score
89 vs 90

Hardware

gemma4:12b GPT-20B:20b
MachineASUSHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUIntel Gen Intel® Core™ i7-12700AMD Ryzen 9 9955HX3D 16-Core Processor
Cores2032
RAM30 GB31 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

gemma4:12b GPT-20B:20b
Tokens/sec74.436.9
First chunk152 ms902 ms
TTFT30.0 s4.2 s
Load time0.0 s19.5 s
Memory usage0.8 GB13.1 GB
Memory %3%42%

HW Fit Score Breakdown

gemma4:12b

Speed
50/50
TTFT
0/20
Memory
30/30

GPT-20B:20b

Speed
47/50
TTFT
7/20
Memory
27/30

Quality

gemma4:12b

Reasoning
18/20
Coding
15/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
10/10
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
View gemma4:12b details | View GPT-20B:20b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest