Back to leaderboard

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

qwen/qwen3-30b-a3b-2507

LM-STUDIO GGUF

qwen3moe · 30B · Q4_K_M

Excellent

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
74 vs 89
Hardware Fit
99 vs 84
Quality Score
63 vs 91

Hardware

llama3.2:3b qwen/qwen3-30b-a3b…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUS
CPUCortex-A78AEAMD Ryzen 7 7800X3D 8-Core Processor
Cores616
RAM7 GB31 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 4090, Raphael
OSUbuntu 22.04.5 LTScachyos rolling
Archarm64x64
Power Modebalancedperformance

Performance

llama3.2:3b qwen/qwen3-30b-a3b…
Tokens/sec21.1104.5
First chunk1032 ms5 ms
TTFT1.0 s163 ms
Load time8.4 sN/A
Memory usage2.4 GB22.1 GB
Memory %32%73%

HW Fit Score Breakdown

llama3.2:3b

Speed
50/50
TTFT
20/20
Memory
29/30

qwen/qwen3-30b-a3b-2507

Speed
50/50
TTFT
20/20
Memory
14/30

Quality

llama3.2:3b

Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

qwen/qwen3-30b-a3b-2507

Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View llama3.2:3b details | View qwen/qwen3-30b-a3b… 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