Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

Global Score
32 vs 81
Hardware Fit
98 vs 100
Quality Score
4 vs 73

Hardware

qwen3:4b gemma3n:latest
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperSupermicro AS -2015HS-TNR
CPUCortex-A78AEAMD EPYC 9654P 96-Core Processor
Cores664
RAM7 GB128 GB
GPUIntegrated / UnknownGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSUbuntu 22.04.5 LTSUbuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3:4b gemma3n:latest
Tokens/sec17.9108.7
First chunk950 ms333 ms
TTFT950 ms333 ms
Load time9.7 s4.5 s
Memory usage3.0 GB8.6 GB
Memory %40%7%

HW Fit Score Breakdown

qwen3:4b

Speed
50/50
TTFT
20/20
Memory
28/30

gemma3n:latest

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

Quality

qwen3:4b

Reasoning
4/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

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
View qwen3:4b details | View gemma3n:latest 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