gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
hf.co/ornith-ai/Ornith-1.0-9B-GGUF:Q4_K_M
OLLAMA GGUFqwen35 · 8.95B · unknown
Aug 23, 2026 · Apple M1 Pro
Global Score
81 vs 62
Hardware Fit
100 vs 96
Quality Score
73 vs 47
Hardware
gemma3n:latest hf.co/ornith-ai/Or…
MachineSupermicro AS -2015HS-TNRMacBook Pro
CPUAMD EPYC 9654P 96-Core ProcessorApple M1 Pro
Cores6410
RAM128 GB16 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Apple M1 Pro
OSUbuntu 24.04.3 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced
Performance
gemma3n:latest hf.co/ornith-ai/Or…
Tokens/sec108.722.3
First chunk333 ms324 ms
TTFT333 ms324 ms
Load time4.5 s3.2 s
Memory usage8.6 GB6.9 GB
Memory %7%43%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
hf.co/ornith-ai/Ornith-…
Speed
49/50
TTFT
20/20
Memory
27/30
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/ornith-ai/Ornith-…
Reasoning
16/20
Coding
14/20
Instruction
3/20
Structured
1/15
Math
13/15
Multilingual
0/10
Reasoning: Strong Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
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