Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

qwen/qwen3-30b-a3b-2507

LM-STUDIO GGUF

qwen3moe · 30B · Q4_K_M

Excellent

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
53 vs 89
Hardware Fit
82 vs 84
Quality Score
41 vs 91

Hardware

qwen3.5:4b-mlx qwen/qwen3-30b-a3b…
MachineMac miniASUS
CPUApple M2AMD Ryzen 7 7800X3D 8-Core Processor
Cores816
RAM8 GB31 GB
GPUApple M2NVIDIA GeForce RTX 4090, Raphael
OSmacOS 26.5.2cachyos rolling
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5:4b-mlx qwen/qwen3-30b-a3b…
Tokens/sec24.7104.5
First chunk302 ms5 ms
TTFT7.4 s163 ms
Load time3.2 sN/A
Memory usage3.8 GB22.1 GB
Memory %47%73%

HW Fit Score Breakdown

qwen3.5:4b-mlx

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

qwen/qwen3-30b-a3b-2507

Speed
50/50
TTFT
20/20
Memory
14/30

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/qwen3-30b-a3b-2507

Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
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/qwen3-30b-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