Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
78 vs 74
Hardware Fit
86 vs 99
Quality Score
74 vs 63

Hardware

qwen3:8b llama3.2:3b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD Ryzen 9 3900X 12-Core ProcessorCortex-A78AE
Cores246
RAM64 GB7 GB
GPUNVIDIA GeForce RTX 4060 TiIntegrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:8b llama3.2:3b
Tokens/sec48.521.1
First chunk202 ms1032 ms
TTFT4.3 s1.0 s
Load time4.2 s8.4 s
Memory usage5.5 GB2.4 GB
Memory %9%32%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
6/20
Memory
30/30

llama3.2:3b

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

Quality

qwen3:8b

Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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

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