Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score
81 vs 71
Hardware Fit
100 vs 42
Quality Score
73 vs 84

Hardware

gemma3n:latest qwen3:30b-a3b-inst…
MachineSupermicro AS -2015HS-TNRDell Inc. PowerEdge R820
CPUAMD EPYC 9654P 96-Core ProcessorIntel Xeon® E5-4620 0
Cores6464
RAM128 GB256 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSUbuntu 24.04.3 LTSMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modeperformancebalanced

Performance

gemma3n:latest qwen3:30b-a3b-inst…
Tokens/sec108.74.0
First chunk333 ms2070 ms
TTFT333 ms2.1 s
Load time4.5 s44.5 s
Memory usage8.6 GB17.7 GB
Memory %7%7%

HW Fit Score Breakdown

gemma3n:latest

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

qwen3:30b-a3b-instruct-…

Speed
3/50
TTFT
9/20
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

qwen3:30b-a3b-instruct-…

Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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