Back to leaderboard

qwen2.5:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

gemma-4-e2b-it-qat

LM-STUDIO GGUF

gemma4 · Q4_K_XL

Excellent

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
77 vs 81
Hardware Fit
100 vs 90
Quality Score
67 vs 77

Hardware

qwen2.5:3b gemma-4-e2b-it-qat
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperDocker Container
CPUCortex-A78AEIntel Gen Intel® Core™ i9-11900H
Cores616
RAM7 GB15 GB
GPUIntegrated / UnknownTigerLake-H GT1 [UHD Graphics]
OSUbuntu 22.04.5 LTSUbuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen2.5:3b gemma-4-e2b-it-qat
Tokens/sec21.422.2
First chunk1006 ms67 ms
TTFT1.0 s1.1 s
Load time6.4 s5.4 s
Memory usage2.0 GB0.0 GB
Memory %27%0%

HW Fit Score Breakdown

qwen2.5:3b

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

gemma-4-e2b-it-qat

Speed
40/50
TTFT
20/20
Memory
30/30

Quality

qwen2.5:3b

Reasoning
12/20
Coding
14/20
Instruction
11/20
Structured
15/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

gemma-4-e2b-it-qat

Reasoning
10/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen2.5:3b details | View gemma-4-e2b-it-qat 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