qwen3.5-2b-mlx

qwen3_5 · 2B · 8bit

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 3, 2026 · Submitted by Topaz750

Top 45% Compare

Global Score

70 /100

Good

Hardware Fit

93/100

Quality

60/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 32.9
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±18.7
First chunk latency Delay before the first streamed chunk arrives from runtime: 3.1 s
Time to first token How fast the model starts responding — lower is better: 3.1 s
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 2.5 GB (8%)
Total tokens Total number of tokens generated across all benchmark prompts: 725

Score breakdown

Speed

50/50

Time to first token

13/20

Memory

30/30

Quality

Reasoning

11/20

Coding

9/20

Instruction following

14/20

Structured output

14/15

Math

3/15

Multilingual

9/10

Category levels

Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

Metadata

Spec version: 0.2.0
Runtime: LM Studio 0.4.6+1
Model format: MLX
Hardware profile: BALANCED
Result hash: bf01008a0cc32a4a0d47a944417e542f4a94b4bbe1a9bb48708def90265250c7

Interpretation

Hardware fit: 93/100. Overall suitability: GOOD (Global 70/100). Category profile: Reasoning: Adequate, Coding: Weak, Instruction Following: Adequate, Structured Output: Strong, Math: Poor, Multilingual: Strong.

Warnings

Token speed is unstable (stddev 18.7 tok/s, mean 32.9 tok/s) — may indicate thermal throttling or memory pressure.

Bench Environment

Power: AC CPU load: avg 14% (peak 19%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest