Qwen3-Next-80B:80B

qwen3next · 79.7B · unknown

GMKtec NucBox EVO-T2S (Intel Core™ Ultra X7 358H)

64 GB · Microsoft Windows 11 Pro 10.0.26200

Tested on August 18, 2026 · Submitted by Haval

Top 99% Compare

Global Score

19 /100

Not Rec.

Hardware Fit

52/100

Quality

5/100

Get this model

🦙

Ollama

ollama pull Qwen3-Next-80B:80B

View on Ollama Library

ollama.com/library/Qwen3-Next-80B

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: GMKtec NucBox EVO-T2S
CPU: Intel Core™ Ultra X7 358H
Cores: 16 total (16 perf)
Frequency: 1.9 GHz
RAM: 64 GB LPDDR5
GPU: Intel(R) Arc(TM) B390 GPU
OS: Microsoft Windows 11 Pro 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 1000000.0
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: 5.6 s
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: 72.5 s
Memory usage RAM consumed during inference — percentage of total system memory: 61.3 GB (97%)
Total tokens Total number of tokens generated across all benchmark prompts: 154

Score breakdown

Speed

50/50

Time to first token

0/20

Memory

2/30

Quality

Reasoning

0/20

Coding

0/20

Instruction following

5/20

Structured output

0/15

Math

0/15

Multilingual

0/10

Category levels

Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.32.9
Model format: GGUF
Hardware profile: HIGH-END
Result hash: b24a64e9f44c9fdb9eb055ad8bb1c2d42818c08f0d33627bb0000f2e21dd2a6a

Interpretation

Hardware fit: 52/100. Overall suitability: NOT RECOMMENDED (Global 19/100). Category profile: Reasoning: Poor, Coding: Poor, Instruction Following: Weak, Structured Output: Poor, Math: Poor, Multilingual: Poor. Warning: model produced very low accuracy on quality tasks — results may be unusable despite good hardware performance.

Warnings

Model produced very low accuracy on quality tasks — results may be unusable despite good hardware performance.
Significant swap activity during benchmark (+7.5 GB). Model may exceed available RAM — results are severely degraded.

Disqualifiers

Time to first token too high: 30000ms (maximum: 15770ms for HIGH-END profile)
Memory usage critical: model delta +97%

Bench Environment

Swap delta: +7.5 GB CPU load: avg 48% (peak 55%)

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