Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

mistral-nemo:12b

OLLAMA GGUF

llama · 12.2B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score
81 vs 71
Hardware Fit
100 vs 86
Quality Score
73 vs 65

Hardware

gemma3n:latest mistral-nemo:12b
MachineSupermicro AS -2015HS-TNRMacBook Air
CPUAMD EPYC 9654P 96-Core ProcessorApple M4
Cores6410
RAM128 GB32 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Apple M4
OSUbuntu 24.04.3 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

gemma3n:latest mistral-nemo:12b
Tokens/sec108.714.6
First chunk333 msN/A
TTFT333 ms371 ms
Load time4.5 s1.0 s
Memory usage8.6 GB13.3 GB
Memory %7%42%

HW Fit Score Breakdown

gemma3n:latest

Speed
50/50
TTFT
20/20
Memory
30/30

mistral-nemo:12b

Speed
26/50
TTFT
30/20
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

mistral-nemo:12b

Reasoning
12/20
Coding
13/20
Instruction
11/20
Structured
15/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest