Back to leaderboard

qwen2.5:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Excellent

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
77 vs 89
Hardware Fit
100 vs 95
Quality Score
67 vs 87

Hardware

qwen2.5:3b gemma4:26b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperAZW GTR Pro
CPUCortex-A78AEAMD RYZEN AI MAX+ 395
Cores632
RAM7 GB125 GB
GPUIntegrated / UnknownRadeon 8060S
OSUbuntu 22.04.5 LTSUbuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen2.5:3b gemma4:26b
Tokens/sec21.448.3
First chunk1006 ms346 ms
TTFT1.0 s346 ms
Load time6.4 s4.4 s
Memory usage2.0 GB36.1 GB
Memory %27%29%

HW Fit Score Breakdown

qwen2.5:3b

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

gemma4:26b

Speed
45/50
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

gemma4:26b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
14/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen2.5:3b details | View gemma4:26b 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