qwen/qwen3.5-35b-a3b

qwen35moe · 35B · Q6_K

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

32 GB · Microsoft Windows 11 Home 10.0.26200

Tested on September 19, 2026

Top 61% Compare

Global Score

72 /100

Not Rec.

Hardware Fit

35/100

Quality

88/100

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 total (16 perf)
Frequency: 3.8 GHz
RAM: 32 GB DDR4
GPU: AMD Radeon RX 9060 XT
OS: Microsoft Windows 11 Home 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 8.3
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: 32 ms
Time to first token How fast the model starts responding — lower is better: 2.0 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: 28.9 GB (91%)
Total tokens Total number of tokens generated across all benchmark prompts: 1134

Score breakdown

Speed

13/50

Time to first token

17/20

Memory

5/30

Quality

Reasoning

16/20

Coding

19/20

Instruction following

16/20

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: c2be0fc1adf98b6ed1fa4c18736b3780585c7473fc159c4ce158fe606fffb5dd

Interpretation

Hardware fit: 35/100. Overall suitability: NOT RECOMMENDED (Global 72/100). 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.

Disqualifiers

Memory usage critical: model delta +91%

Bench Environment

CPU load: avg 9% (peak 13%)

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