gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Sep 15, 2026 · Intel Core™ i5-14400F
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Apr 28, 2026 · Intel Xeon® Gold 6230
Global Score
94 vs 80
Hardware Fit
97 vs 85
Quality Score
93 vs 78
Hardware
gpt-oss:20b qwen3:8b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4HP HP Z8 G4 Workstation
CPUIntel Core™ i5-14400FIntel Xeon® Gold 6230
Cores1680
RAM32 GB252 GB
GPUNVIDIA GeForce RTX 5060 TiTU104GL [Quadro RTX 5000]
OSMicrosoft Windows 11 Professionnel 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power
Performance
gpt-oss:20b qwen3:8b
Tokens/sec80.465.1
First chunk139 ms289 ms
TTFT1.6 s4.2 s
Load time11.6 s4.6 s
Memory usage11.9 GB5.6 GB
Memory %37%2%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
19/20
Memory
28/30
qwen3:8b
Speed
50/50
TTFT
5/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:8b
Reasoning
17/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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