Back to leaderboard

qwen3-vl-4b-instruct

LM-STUDIO GGUF

qwen3vl · 4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

gemma4:latest

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Jun 5, 2026 · AMD Ryzen 7 5800H

Global Score
87 vs 89
Hardware Fit
100 vs 83
Quality Score
81 vs 92

Hardware

qwen3-vl-4b-instruct gemma4:latest
MachineMac StudioLENOVO 82JQ
CPUApple M2 MaxAMD Ryzen 7 5800H
Cores1216
RAM96 GB16 GB
GPUApple M2 MaxNVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 26.1Microsoft Windows 11 家庭版 中文版 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-vl-4b-instruct gemma4:latest
Tokens/sec71.646.3
First chunk5 ms824 ms
TTFT157 ms3.8 s
Load timeN/A21.0 s
Memory usage20.5 GB8.9 GB
Memory %21%56%

HW Fit Score Breakdown

qwen3-vl-4b-instruct

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

gemma4:latest

Speed
50/50
TTFT
11/20
Memory
22/30

Quality

qwen3-vl-4b-instruct

Reasoning
15/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma4:latest

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-vl-4b-instruct details | View gemma4:latest 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