Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
68 vs 84
Hardware Fit
93 vs 79
Quality Score
57 vs 86

Hardware

google/gemma-4-e4b qwen/qwen3.6-35b-a3b
MachineLENOVO 82JQASUS
CPUAMD Ryzen 7 5800HAMD Ryzen 7 7800X3D 8-Core Processor
Cores1616
RAM16 GB31 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

google/gemma-4-e4b qwen/qwen3.6-35b-a3b
Tokens/sec26.2115.8
First chunk17 ms9 ms
TTFT572 ms310 ms
Load timeN/AN/A
Memory usage6.5 GB25.3 GB
Memory %41%83%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen/qwen3.6-35b-a3b

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

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

qwen/qwen3.6-35b-a3b

Reasoning
16/20
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 qwen/qwen3.6-35b-a3b 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