llama3.2:latest

llama · 3.2B · Q4_K_M

Micro-Star International Co., Ltd. MS-7B79 (AMD Ryzen 5 2600X Six-Core Processor)

16 GB · Microsoft Windows 11 Famille 10.0.26200

Tested on May 27, 2026

Top 36% Compare

Global Score

76 /100

Good

Hardware Fit

100/100

Quality

65/100

Get this model

🦙

Ollama

ollama pull llama3.2:latest

View on Ollama Library

ollama.com/library/llama3.2

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Micro-Star International Co., Ltd. MS-7B79
CPU: AMD Ryzen 5 2600X Six-Core Processor
Cores: 12 total (12 perf)
Frequency: 3.6 GHz
RAM: 16 GB DDR4
GPU: NVIDIA GeForce GTX 1080
OS: Microsoft Windows 11 Famille 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 57.0
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±2.8
First chunk latency Delay before the first streamed chunk arrives from runtime: 264 ms
Time to first token How fast the model starts responding — lower is better: 264 ms
Load time Time to load the model into memory before inference: 9.7 s
Memory usage RAM consumed during inference — percentage of total system memory: 2.6 GB (16%)
Total tokens Total number of tokens generated across all benchmark prompts: 1069

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

11/20

Coding

15/20

Instruction following

15/20

Structured output

12/15

Math

3/15

Multilingual

9/10

Category levels

Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.24.0
Model format: GGUF
Hardware profile: ENTRY
Result hash: 60f27b099c6ddf64f1c4943e01dbfc827bc306ee67955d5cea1ccb2d02bdcbc2

Interpretation

Hardware fit: 100/100. Overall suitability: GOOD (Global 76/100). Category profile: Reasoning: Adequate, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Poor, Multilingual: Strong.

Bench Environment

CPU load: avg 22% (peak 26%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest