Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

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

Global Score
62 vs 87
Hardware Fit
77 vs 81
Quality Score
55 vs 90

Hardware

google/gemma-4-e4b GPT-20B:20b
MachineLENOVO 82JQHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUAMD Ryzen 7 5800HAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1632
RAM16 GB31 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b GPT-20B:20b
Tokens/sec27.636.9
First chunk23 ms902 ms
TTFT480 ms4.2 s
Load timeN/A19.5 s
Memory usage13.2 GB13.1 GB
Memory %83%42%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

GPT-20B:20b

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

Quality

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

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 google/gemma-4-e4b 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