gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
qwen3-next:80b-a3b-instruct-q4_K_M
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 18, 2026 · Intel Xeon® E5-2637 v3
Global Score
81 vs 78
Hardware Fit
59 vs 51
Quality Score
91 vs 89
Hardware
gpt-oss:20b qwen3-next:80b-a3b…
MachineGMKtec NucBox EVO-T2SDell Inc. Precision Tower 7910
CPUIntel Core™ Ultra X7 358HIntel Xeon® E5-2637 v3
Cores1616
RAM64 GB96 GB
GPUIntel(R) Arc(TM) B390 GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
gpt-oss:20b qwen3-next:80b-a3b…
Tokens/sec19.18.7
First chunk1985 ms1251 ms
TTFT11.1 s1.3 s
Load time7.7 s61.6 s
Memory usage12.9 GB48.3 GB
Memory %20%50%
HW Fit Score Breakdown
gpt-oss:20b
Speed
26/50
TTFT
3/20
Memory
30/30
qwen3-next:80b-a3b-inst…
Speed
9/50
TTFT
17/20
Memory
25/30
Quality
gpt-oss:20b
Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-next:80b-a3b-inst…
Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
13/15
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