qwen3.5:9b-mlx

nvfp4

THINKING MODEL

MacBook Pro (Apple M1 Pro)

16 GB · macOS 26.6.2

Tested on August 26, 2026 · Submitted by AAA

Top 86% Compare

Global Score

54 /100

Marginal

Hardware Fit

81/100

Quality

43/100

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: 25.2
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.0
First chunk latency Delay before the first streamed chunk arrives from runtime: 341 ms
Time to first token How fast the model starts responding — lower is better: 6.3 s
Load time Time to load the model into memory before inference: 3.4 s
Memory usage RAM consumed during inference — percentage of total system memory: 8.4 GB (52%)
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: ~711

Score breakdown

Speed

50/50

Time to first token

7/20

Memory

24/30

Quality

Reasoning

14/20

Coding

2/20

Instruction following

4/20

Structured output

4/15

Math

10/15

Multilingual

9/10

Category levels

Reasoning: Adequate Coding: Poor Instruction Following: Poor 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: e20ba5c7478a822defbf97b9dd4a34dbfc7ccd0fe243402b38a8fcbe68687f60

Interpretation

Hardware fit: 81/100. Overall suitability: MARGINAL (Global 54/100). Category profile: Reasoning: Adequate, Coding: Poor, Instruction Following: Poor, Structured Output: Weak, Math: Adequate, Multilingual: Strong.

Bench Environment

Power: AC CPU load: avg 8% (peak 11%)

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