qwen3.5:4b-mlx

nvfp4

THINKING MODEL

MacBook Pro (Apple M1 Pro)

16 GB · macOS 26.6.2

Tested on August 25, 2026 · Submitted by AAA

Top 65% Compare

Global Score

68 /100

Good

Hardware Fit

91/100

Quality

58/100

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 Pro
CPU: Apple M1 Pro
Cores: 10 total (8 perf + 2 eff)
Frequency: 2.4 GHz
RAM: 16 GB LPDDR5
GPU: Apple M1 Pro
OS: macOS 26.6.2
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 42.2
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 201 ms
Time to first token How fast the model starts responding — lower is better: 4.4 s
Load time Time to load the model into memory before inference: 0.0 s
Memory usage RAM consumed during inference — percentage of total system memory: 3.8 GB (24%)
Total tokens Total number of tokens generated across all benchmark prompts: 1429
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~727

Score breakdown

Speed

50/50

Time to first token

11/20

Memory

30/30

Quality

Reasoning

16/20

Coding

2/20

Instruction following

13/20

Structured output

7/15

Math

11/15

Multilingual

9/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.32.15
Model format: GGUF
Hardware profile: ENTRY
Result hash: 354815f18951b4cc97b8cd05e4fa6ff25b76ae1487922996ef6c76b2a81dc7a2

Interpretation

Hardware fit: 91/100. Overall suitability: GOOD (Global 68/100). Category profile: Reasoning: Strong, Coding: Poor, Instruction Following: Adequate, Structured Output: Weak, Math: Adequate, Multilingual: Strong.

Bench Environment

Power: AC CPU load: avg 33% (peak 41%)

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