gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_M
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 21, 2026 · AMD RYZEN AI MAX+ 395
Global Score
81 vs 68
Hardware Fit
100 vs 69
Quality Score
73 vs 67
Hardware
gemma3n:latest hf.co/unsloth/Qwen…
MachineSupermicro AS -2015HS-TNRAZW GTR Pro
CPUAMD EPYC 9654P 96-Core ProcessorAMD RYZEN AI MAX+ 395
Cores6432
RAM128 GB125 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Radeon 8060S
OSUbuntu 24.04.3 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modeperformancelow-power
Performance
gemma3n:latest hf.co/unsloth/Qwen…
Tokens/sec108.721.1
First chunk333 ms571 ms
TTFT333 ms571 ms
Load time4.5 s4.9 s
Memory usage8.6 GB22.7 GB
Memory %7%18%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
hf.co/unsloth/Qwen3.8-2…
Speed
20/50
TTFT
19/20
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
hf.co/unsloth/Qwen3.8-2…
Reasoning
12/20
Coding
10/20
Instruction
10/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate 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