Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

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

Hardware

google/gemma-4-e4b spark-x2.5-4b
MachineLENOVO 82JQASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUAMD Ryzen 7 5800HAMD Ryzen 7 4800H
Cores1616
RAM16 GB15 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b spark-x2.5-4b
Tokens/sec26.248.9
First chunk17 ms20 ms
TTFT572 ms168 ms
Load timeN/AN/A
Memory usage6.5 GB9.4 GB
Memory %41%61%

HW Fit Score Breakdown

google/gemma-4-e4b

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

spark-x2.5-4b

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

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

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