qwen3-next:80b-a3b-instruct-q4_K_M
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 23, 2026 · Intel Xeon® E5-4650 v2
GPT-OSS-120B:120B
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
Global Score
74 vs 67
Hardware Fit
42 vs 21
Quality Score
87 vs 87
Hardware
qwen3-next:80b-a3b… GPT-OSS-120B:120B
MachineDell Inc. PowerEdge R820GMKtec NucBox EVO-T2S
CPUIntel Xeon® E5-4650 v2Intel Core™ Ultra X7 358H
Cores8016
RAM256 GB64 GB
GPUMicrosoft Basic Display AdapterIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen3-next:80b-a3b… GPT-OSS-120B:120B
Tokens/sec3.911.7
First chunk2089 ms4289 ms
TTFT2.1 s9.2 s
Load time73.3 s84.1 s
Memory usage46.9 GB61.0 GB
Memory %18%96%
HW Fit Score Breakdown
qwen3-next:80b-a3b-inst…
Speed
3/50
TTFT
9/20
Memory
30/30
GPT-OSS-120B:120B
Speed
15/50
TTFT
4/20
Memory
2/30
Quality
qwen3-next:80b-a3b-inst…
Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
GPT-OSS-120B:120B
Reasoning
18/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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