qwen/qwen3.6-27b

qwen35 · 27B · Q4_K_M

GMKtec EVO-X3 (AMD RYZEN AI MAX+ 395)

120 GB · Microsoft Windows 11 Pro 10.0.26300

Tested on November 1, 2026 · Submitted by Idiopathic

Top 53% Compare

Global Score

76 /100

Not Rec.

Hardware Fit

47/100

Quality

89/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: GMKtec EVO-X3
CPU: AMD RYZEN AI MAX+ 395
Cores: 32 total (32 perf)
Frequency: 3 GHz
RAM: 120 GB LPDDR5
GPU: AMD Radeon(TM) 8060S Graphics
OS: Microsoft Windows 11 Pro 10.0.26300
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 10.7
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: 35 ms
Time to first token How fast the model starts responding — lower is better: 885 ms
Load time Time to load the model into memory before inference: 127.6 s
Memory usage RAM consumed during inference — percentage of total system memory: 67.5 GB (56%)
Total tokens Total number of tokens generated across all benchmark prompts: 1233

Score breakdown

Speed

9/50

Time to first token

16/20

Memory

22/30

Quality

Reasoning

18/20

Coding

18/20

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: HIGH-END
Result hash: 6aefdb942724c2b118bebb606f544ace9703c6207c32d7dd73257887797e0076

Interpretation

Hardware fit: 47/100. Overall suitability: NOT RECOMMENDED (Global 76/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Disqualifiers

Model load time too high: 127579ms (maximum: 90000ms for HIGH-END profile)

Bench Environment

CPU load: avg 30% (peak 35%)

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