qwen3.5:4b

qwen35 · 4.7B · Q4_K_M

THINKING MODEL ECO MODE

AZW GTR Pro (AMD RYZEN AI MAX+ 395)

125 GB · Ubuntu 24.04.4 LTS

Tested on March 5, 2026

Top 55% Compare

Global Score

65 /100

Not Rec.

Hardware Fit

73/100

Quality

62/100

Get this model

🦙

Ollama

ollama pull qwen3.5:4b

View on Ollama Library

ollama.com/library/qwen3.5

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: AZW GTR Pro
CPU: AMD RYZEN AI MAX+ 395
Cores: 32 threads (16 cores)
Frequency: 3 GHz
RAM: 125 GB
GPU: AMD Radeon 8060S
OS: Ubuntu 24.04.4 LTS
Arch: x64
Power Mode: low-power

Performance

Tokens/sec Tokens generated per second — higher is better: 45.7
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: 180 ms
Time to first token How fast the model starts responding — lower is better: 30.0 s
Load time Time to load the model into memory before inference: 5.3 s
Memory usage RAM consumed during inference — percentage of total system memory: 16.2 GB (13%)
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: ~745

Score breakdown

Speed

43/50

Time to first token

0/20

Memory

30/30

Quality

Reasoning

17/20

Coding

1/20

Instruction following

13/20

Structured output

8/15

Math

13/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 8a729467836dd9c1de490d490db3b112077a50bdfa1d119fe9c81a174bfa2e39

Interpretation

Hardware fit: 73/100. Overall suitability: NOT RECOMMENDED (Global 65/100). Category profile: Reasoning: Strong, Coding: Poor, Instruction Following: Adequate, Structured Output: Adequate, Math: Strong, Multilingual: Strong.

Warnings

System was in low-power mode during this benchmark.
CPU appears throttled (2.2 GHz current vs 3.0 GHz nominal, 73%).

Disqualifiers

Time to first token too high: 30000ms (maximum: 10000ms for HIGH-END profile)

Bench Environment

Thermal: nominal CPU load: avg 4% (peak 4%)

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