Qwen3-Next-80B:80B
OLLAMA GGUFqwen3next · 79.7B · unknown
Aug 18, 2026 · Intel Core™ Ultra X7 358H
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
19 vs 81
Hardware Fit
52 vs 100
Quality Score
5 vs 73
Hardware
Qwen3-Next-80B:80B gemma3n:latest
MachineGMKtec NucBox EVO-T2SSupermicro AS -2015HS-TNR
CPUIntel Core™ Ultra X7 358HAMD EPYC 9654P 96-Core Processor
Cores1664
RAM64 GB128 GB
GPUIntel(R) Arc(TM) B390 GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.3 LTS
Archx64x64
Power Modebalancedperformance
Performance
Qwen3-Next-80B:80B gemma3n:latest
Tokens/sec1000000.0108.7
First chunk5563 ms333 ms
TTFT30.0 s333 ms
Load time72.5 s4.5 s
Memory usage61.3 GB8.6 GB
Memory %97%7%
HW Fit Score Breakdown
Qwen3-Next-80B:80B
Speed
50/50
TTFT
0/20
Memory
2/30
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
Qwen3-Next-80B:80B
Reasoning
0/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest