Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jul 29, 2026 · Intel Xeon® E5-2637 v3

Global Score
65 vs 83
Hardware Fit
88 vs 66
Quality Score
55 vs 90

Hardware

qwen3.5-2b-mlx qwen3:30b-a3b-inst…
MachineMac miniDell Inc. Precision Tower 7910
CPUApple M4 ProIntel Xeon® E5-2637 v3
Cores1416
RAM64 GB96 GB
GPUApple M4 ProNVIDIA GeForce RTX 5060 Ti
OSmacOS 15.7.4Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-2b-mlx qwen3:30b-a3b-inst…
Tokens/sec48.917.7
First chunk4208 ms1244 ms
TTFT4.2 s1.2 s
Load timeN/A20.5 s
Memory usage1.6 GB20.6 GB
Memory %3%21%

HW Fit Score Breakdown

qwen3.5-2b-mlx

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

qwen3:30b-a3b-instruct-…

Speed
19/50
TTFT
17/20
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

qwen3:30b-a3b-instruct-…

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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