qwen/qwen3.6-35b-a3b:2

qwen35moe · 35B · Q4_K_M

ECO MODE

System manufacturer (AMD Ryzen 7 5800X 8-Core Processor)

31 GB · Ubuntu 26.04.1 LTS

Tested on September 19, 2026

Top 58% Compare

Global Score

73 /100

Good

Hardware Fit

50/100

Quality

83/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: System manufacturer
CPU: AMD Ryzen 7 5800X 8-Core Processor
Cores: 16 threads (8 cores)
Frequency: 3.8 GHz
RAM: 31 GB
GPU: Navi 44 [Radeon RX 9060 XT]
OS: Ubuntu 26.04.1 LTS
Arch: x64
Power Mode: low-power

Performance

Tokens/sec Tokens generated per second — higher is better: 10.5
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.5
First chunk latency Delay before the first streamed chunk arrives from runtime: 4 ms
Time to first token How fast the model starts responding — lower is better: 1.7 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: 21.4 GB (69%)
Total tokens Total number of tokens generated across all benchmark prompts: 1044

Score breakdown

Speed

16/50

Time to first token

18/20

Memory

16/30

Quality

Reasoning

16/20

Coding

15/20

Instruction following

15/20

Structured output

15/15

Math

12/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio
Model format: GGUF
Hardware profile: BALANCED
Result hash: 657bf9f455091c7a76317b9c15eb3383fdcb6323fd48acf020ccb9803b7a4596

Interpretation

Hardware fit: 50/100. Overall suitability: GOOD (Global 73/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.
System was in low-power mode during this benchmark.

Bench Environment

Thermal: nominal CPU load: avg 19% (peak 23%)

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