Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

GPT-120B:120b

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Not Rec.

Aug 18, 2026 · Intel Core™ i7-14700F

Global Score
68 vs 66
Hardware Fit
93 vs 14
Quality Score
57 vs 88

Hardware

google/gemma-4-e4b GPT-120B:120b
MachineLENOVO 82JQHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUAMD Ryzen 7 5800HIntel Core™ i7-14700F
Cores1628
RAM16 GB64 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 5080
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b GPT-120B:120b
Tokens/sec26.210.1
First chunk17 ms6562 ms
TTFT572 ms10.3 s
Load timeN/A49.8 s
Memory usage6.5 GB61.5 GB
Memory %41%96%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

GPT-120B:120b

Speed
10/50
TTFT
2/20
Memory
2/30

Quality

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor

GPT-120B:120b

Reasoning
18/20
Coding
19/20
Instruction
11/20
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-120B:120b 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