Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000

Global Score
81 vs 65
Hardware Fit
100 vs 87
Quality Score
73 vs 56

Hardware

gemma3n:latest qwen2.5:1.5b
MachineSupermicro AS -2015HS-TNRShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUAMD EPYC 9654P 96-Core ProcessorZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores648
RAM128 GB30 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]ZX C-1190
OSUbuntu 24.04.3 LTSMicrosoft Windows 11 Pro 10.0.26100
Archx64x64
Power Modeperformancebalanced

Performance

gemma3n:latest qwen2.5:1.5b
Tokens/sec108.716.8
First chunk333 ms941 ms
TTFT333 ms941 ms
Load time4.5 s0.2 s
Memory usage8.6 GB1.0 GB
Memory %7%3%

HW Fit Score Breakdown

gemma3n:latest

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

qwen2.5:1.5b

Speed
37/50
TTFT
20/20
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

qwen2.5:1.5b

Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View gemma3n:latest details | View qwen2.5:1.5b 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