Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

qwen2-57b:57B

OLLAMA GGUF

qwen2moe · 57.4B · Q4_K_M

Good

Aug 18, 2026 · Intel Core™ Ultra X7 358H

Global Score
81 vs 67
Hardware Fit
100 vs 51
Quality Score
73 vs 74

Hardware

gemma3n:latest qwen2-57b:57B
MachineSupermicro AS -2015HS-TNRGMKtec NucBox EVO-T2S
CPUAMD EPYC 9654P 96-Core ProcessorIntel Core™ Ultra X7 358H
Cores6416
RAM128 GB64 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Intel(R) Arc(TM) B390 GPU
OSUbuntu 24.04.3 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

gemma3n:latest qwen2-57b:57B
Tokens/sec108.78.6
First chunk333 ms1573 ms
TTFT333 ms1.6 s
Load time4.5 s29.0 s
Memory usage8.6 GB32.8 GB
Memory %7%52%

HW Fit Score Breakdown

gemma3n:latest

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

qwen2-57b:57B

Speed
10/50
TTFT
17/20
Memory
24/30

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

qwen2-57b:57B

Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate 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