Qwen3-Next-80B:80B
OLLAMA GGUFqwen3next · 79.7B · unknown
Aug 18, 2026 · Intel Core™ Ultra X7 358H
phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
19 vs 77
Hardware Fit
52 vs 74
Quality Score
5 vs 78
Hardware
Qwen3-Next-80B:80B phi4:14b
MachineGMKtec NucBox EVO-T2SNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ Ultra X7 358HCortex-X925
Cores1620
RAM64 GB122 GB
GPUIntel(R) Arc(TM) B390 GPUDevice 2e12
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
Qwen3-Next-80B:80B phi4:14b
Tokens/sec1000000.022.9
First chunk5563 ms198 ms
TTFT30.0 s198 ms
Load time72.5 s10.3 s
Memory usage61.3 GB14.7 GB
Memory %97%12%
HW Fit Score Breakdown
Qwen3-Next-80B:80B
Speed
50/50
TTFT
0/20
Memory
2/30
phi4:14b
Speed
24/50
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
phi4:14b
Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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