Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

qwen3-coder:30b-a3b-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · Intel Core™ Ultra 9 285HX

Global Score
65 vs 91
Hardware Fit
88 vs 100
Quality Score
55 vs 87

Hardware

qwen3.5-2b-mlx qwen3-coder:30b-a3…
MachineMac miniMicro-Star International Co., Ltd. Titan 18 HX AI A2XWJG
CPUApple M4 ProIntel Core™ Ultra 9 285HX
Cores1424
RAM64 GB63 GB
GPUApple M4 ProIntel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPU
OSmacOS 15.7.4Microsoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-2b-mlx qwen3-coder:30b-a3…
Tokens/sec48.9175.3
First chunk4208 ms224 ms
TTFT4.2 s224 ms
Load timeN/A6.1 s
Memory usage1.6 GB18.7 GB
Memory %3%30%

HW Fit Score Breakdown

qwen3.5-2b-mlx

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

qwen3-coder:30b-a3b-q4_…

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

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

qwen3-coder:30b-a3b-q4_…

Reasoning
16/20
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

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