Qwen3-Next-80B:80B
OLLAMA GGUFqwen3next · 79.7B · unknown
Aug 18, 2026 · Intel Core™ Ultra X7 358H
qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
19 vs 76
Hardware Fit
52 vs 51
Quality Score
5 vs 87
Hardware
Qwen3-Next-80B:80B qwen3-coder:latest
MachineGMKtec NucBox EVO-T2SDell Inc. Inspiron 15 3530
CPUIntel Core™ Ultra X7 358HIntel Gen Intel® Core™ i7-1355U
Cores1612
RAM64 GB31 GB
GPUIntel(R) Arc(TM) B390 GPURaptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 Pro 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
Qwen3-Next-80B:80B qwen3-coder:latest
Tokens/sec1000000.07.6
First chunk5563 ms2037 ms
TTFT30.0 s2.0 s
Load time72.5 s8.7 s
Memory usage61.3 GB18.9 GB
Memory %97%61%
HW Fit Score Breakdown
Qwen3-Next-80B:80B
Speed
50/50
TTFT
0/20
Memory
2/30
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
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
qwen3-coder:latest
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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