gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
81 vs 94
Hardware Fit
100 vs 91
Quality Score
73 vs 95
Hardware
gemma3n:latest gpt-oss:20b
MachineSupermicro AS -2015HS-TNRFramework Desktop (AMD Ryzen AI Max 300 Series)
CPUAMD EPYC 9654P 96-Core ProcessorAMD RYZEN AI MAX+ 395
Cores6432
RAM128 GB64 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]AMD Radeon(TM) 8060S Graphics
OSUbuntu 24.04.3 LTSMicrosoft Windows 11 Pro for Workstations 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
gemma3n:latest gpt-oss:20b
Tokens/sec108.748.0
First chunk333 ms357 ms
TTFT333 ms2.3 s
Load time4.5 s0.2 s
Memory usage8.6 GB16.4 GB
Memory %7%26%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
Quality
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
19/20
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
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