Back to leaderboard

qwen3.5:2b

OLLAMA GGUF

qwen35 · 2.3B · Q8_0

Not Rec.

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
13 vs 62
Hardware Fit
41 vs 77
Quality Score
1 vs 55

Hardware

qwen3.5:2b 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

qwen3.5:2b google/gemma-4-e4b
Tokens/sec4.527.6
First chunk1413 ms23 ms
TTFT31.1 s480 ms
Load time7.1 sN/A
Memory usage3.8 GB13.2 GB
Memory %16%83%

HW Fit Score Breakdown

qwen3.5:2b

Speed
11/50
TTFT
0/20
Memory
30/30

google/gemma-4-e4b

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

Quality

qwen3.5:2b

Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

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 qwen3.5:2b 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