gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
Global Score
81 vs 58
Hardware Fit
100 vs 82
Quality Score
73 vs 48
Hardware
gemma3n:latest qwen3:14b
MachineSupermicro AS -2015HS-TNRMacBook Pro
CPUAMD EPYC 9654P 96-Core ProcessorApple M1 Max
Cores6410
RAM128 GB32 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Apple M1 Max
OSUbuntu 24.04.3 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
gemma3n:latest qwen3:14b
Tokens/sec108.724.4
First chunk333 ms294 ms
TTFT333 ms7.9 s
Load time4.5 s3.7 s
Memory usage8.6 GB13.8 GB
Memory %7%43%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3:14b
Speed
47/50
TTFT
5/20
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
qwen3:14b
Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor 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