Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 7, 2026 · AMD Ryzen 5 5500

Global Score
68 vs 71
Hardware Fit
93 vs 56
Quality Score
57 vs 78

Hardware

google/gemma-4-e4b qwen3.5:9b
MachineLENOVO 82JQSystem manufacturer
CPUAMD Ryzen 7 5800HAMD Ryzen 5 5500
Cores1612
RAM16 GB16 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 3060
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 11 IoT Enterprise LTSC 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b qwen3.5:9b
Tokens/sec26.25.3
First chunk17 ms1624 ms
TTFT572 ms1.6 s
Load timeN/A4.0 s
Memory usage6.5 GB7.9 GB
Memory %41%50%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen3.5:9b

Speed
11/50
TTFT
20/20
Memory
25/30

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

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View google/gemma-4-e4b details | View qwen3.5:9b 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