Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
77 vs 68
Hardware Fit
90 vs 93
Quality Score
71 vs 57

Hardware

spark-x2.5-4b google/gemma-4-e4b
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMLENOVO 82JQ
CPUAMD Ryzen 7 4800HAMD Ryzen 7 5800H
Cores1616
RAM15 GB16 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

spark-x2.5-4b google/gemma-4-e4b
Tokens/sec48.926.2
First chunk20 ms17 ms
TTFT168 ms572 ms
Load timeN/AN/A
Memory usage9.4 GB6.5 GB
Memory %61%41%

HW Fit Score Breakdown

spark-x2.5-4b

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

google/gemma-4-e4b

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

Quality

spark-x2.5-4b

Reasoning
13/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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
View spark-x2.5-4b details | View google/gemma-4-e4b 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