qwen3.5-0.8b-mlx

qwen3_5 · 0.8B · 4bit

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 3, 2026 · Submitted by Topaz750

Top 75% Compare

Global Score

55 /100

Marginal

Hardware Fit

87/100

Quality

41/100

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: 68.2
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±57.7
First chunk latency Delay before the first streamed chunk arrives from runtime: 3.3 s
Time to first token How fast the model starts responding — lower is better: 3.3 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: 0.6 GB (2%)
Total tokens Total number of tokens generated across all benchmark prompts: 976

Score breakdown

Speed

50/50

Time to first token

13/20

Memory

24/30

Quality

Reasoning

8/20

Coding

1/20

Instruction following

12/20

Structured output

12/15

Math

3/15

Multilingual

5/10

Category levels

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

Metadata

Spec version: 0.2.0
Runtime: LM Studio 0.4.6+1
Model format: MLX
Hardware profile: BALANCED
Result hash: 824b1837c1bd2390dbffcef4691a6edcf5c454828b66e9eac9d7e0f8a7faf146

Interpretation

Hardware fit: 87/100. Overall suitability: MARGINAL (Global 55/100). Category profile: Reasoning: Weak, Coding: Poor, Instruction Following: Adequate, Structured Output: Strong, Math: Poor, Multilingual: Adequate.

Warnings

Token speed is unstable (stddev 57.7 tok/s, mean 68.2 tok/s) — may indicate thermal throttling or memory pressure.

Bench Environment

Power: AC CPU load: avg 18% (peak 20%)

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