Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

Global Score
53 vs 92
Hardware Fit
82 vs 95
Quality Score
41 vs 90

Hardware

qwen3.5:4b-mlx qwen/qwen3-vl-30b
MachineMac miniASUS
CPUApple M2AMD Ryzen 5 5500
Cores812
RAM8 GB31 GB
GPUApple M2Navi 44 [Radeon RX 9060 XT]
OSmacOS 26.5.2Nobara Linux 43
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5:4b-mlx qwen/qwen3-vl-30b
Tokens/sec24.724.8
First chunk302 ms11 ms
TTFT7.4 s735 ms
Load time3.2 s11.7 s
Memory usage3.8 GB0.6 GB
Memory %47%2%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

qwen/qwen3-vl-30b

Speed
45/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

qwen/qwen3-vl-30b

Reasoning
19/20
Coding
19/20
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 qwen3.5:4b-mlx details | View qwen/qwen3-vl-30b 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