Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score
62 vs 77
Hardware Fit
77 vs 53
Quality Score
55 vs 87

Hardware

google/gemma-4-e4b qwen3.5:35b
MachineLENOVO 82JQASUS
CPUAMD Ryzen 7 5800HIntel Core™ i5-14600KF
Cores1620
RAM16 GB32 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 4070 Ti SUPER
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b qwen3.5:35b
Tokens/sec27.616.0
First chunk23 ms719 ms
TTFT480 ms719 ms
Load timeN/A17.8 s
Memory usage13.2 GB25.0 GB
Memory %83%79%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen3.5:35b

Speed
23/50
TTFT
20/20
Memory
10/30

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

qwen3.5:35b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View google/gemma-4-e4b details | View qwen3.5:35b 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