Back to leaderboard

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
61 vs 62
Hardware Fit
85 vs 77
Quality Score
51 vs 55

Hardware

qwen3:0.6b google/gemma-4-e4b
MachineLENOVO 20L7CTO1WWLENOVO 82JQ
CPUIntel Core™ i5-8350UAMD Ryzen 7 5800H
Cores816
RAM23 GB16 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]NVIDIA GeForce RTX 3060 Laptop GPU
OSFedora Linux 43Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3:0.6b google/gemma-4-e4b
Tokens/sec27.027.6
First chunk597 ms23 ms
TTFT8.7 s480 ms
Load time1.8 sN/A
Memory usage0.9 GB13.2 GB
Memory %4%83%

HW Fit Score Breakdown

qwen3:0.6b

Speed
50/50
TTFT
5/20
Memory
30/30

google/gemma-4-e4b

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

Quality

qwen3:0.6b

Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate

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
View qwen3:0.6b 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