Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K

Global Score
81 vs 80
Hardware Fit
100 vs 60
Quality Score
73 vs 88

Hardware

gemma3n:latest qwen3-coder:30b
MachineSupermicro AS -2015HS-TNRASUS
CPUAMD EPYC 9654P 96-Core ProcessorIntel Gen Intel® Core™ i7-12700K
Cores6420
RAM128 GB96 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Parsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSUbuntu 24.04.3 LTSMicrosoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

gemma3n:latest qwen3-coder:30b
Tokens/sec108.714.7
First chunk333 ms796 ms
TTFT333 ms796 ms
Load time4.5 s0.2 s
Memory usage8.6 GB17.9 GB
Memory %7%19%

HW Fit Score Breakdown

gemma3n:latest

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

qwen3-coder:30b

Speed
14/50
TTFT
19/20
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

qwen3-coder:30b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View gemma3n:latest details | View qwen3-coder:30b details

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