gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 26, 2026 · Apple M1 Pro
Global Score
81 vs 66
Hardware Fit
100 vs 100
Quality Score
73 vs 52
Hardware
gemma3n:latest hf.co/empero-ai/Qw…
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/empero-ai/Qw…
Tokens/sec108.740.2
First chunk333 ms101 ms
TTFT333 ms101 ms
Load time4.5 s2.6 s
Memory usage8.6 GB4.7 GB
Memory %7%30%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
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/empero-ai/Qwen3.8…
Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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