Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

qwen/qwen3-30b-a3b-2507

LM-STUDIO GGUF

qwen3moe · 30B · Q3_K_L

Excellent

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

Global Score
65 vs 88
Hardware Fit
88 vs 87
Quality Score
55 vs 89

Hardware

qwen3.5-2b-mlx qwen/qwen3-30b-a3b…
MachineMac miniASUS
CPUApple M4 ProAMD Ryzen 7 7800X3D 8-Core Processor
Cores1416
RAM64 GB31 GB
GPUApple M4 ProNVIDIA GeForce RTX 4090, Raphael
OSmacOS 15.7.4cachyos rolling
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5-2b-mlx qwen/qwen3-30b-a3b…
Tokens/sec48.9103.0
First chunk4208 ms3 ms
TTFT4.2 s184 ms
Load timeN/AN/A
Memory usage1.6 GB20.1 GB
Memory %3%66%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

qwen/qwen3-30b-a3b-2507

Speed
50/50
TTFT
20/20
Memory
17/30

Quality

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

qwen/qwen3-30b-a3b-2507

Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5-2b-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