FitMyLLM
Meta/Dense

MetaLlama-3.2-1B

chatThinkingTool UseDistilled
1.2B
Parameters
4K
Context length
13
Benchmarks
6
Quantizations
1.9M
HF downloads
Architecture
Dense
Released
2024-09-25
Layers
16
KV Heads
8
Head Dim
64
Family
llama

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.891.2 GBgood
Q5_K_S5.571.3 GBgood
Q5_K_M5.71.3 GBgood
Q6_K6.561.5 GBexcellent
Q8_08.51.8 GBlossless
FP16162.9 GBlossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN LLAMA-3.2-1B NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (13)

Arena Elo1069
IFEval57.0
GPQA Diamond19.6
BBH8.7
BigCodeBench8.2
MMLU-PRO7.6
MATH7.0
HLE5.3
GPQA3.4
MUSR3.0
LiveCodeBench1.9
AIME0.0
MATH-5000.0

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run llama3.2:1.2b-instruct-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines
HuggingFaceOllama LibraryGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA GeForce GTX 470
1 GB VRAM • 133.9 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 570
1 GB VRAM • 152 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 570 Rev. 2
1 GB VRAM • 152 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 460 v2 ES
1 GB VRAM • 128.3 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 560 OEM
1 GB VRAM • 128.3 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 560 Ti 448
1 GB VRAM • 152 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro FX 5600
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro FX 5600 Mac Edition
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Tesla C870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Tesla D870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Tesla S870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Quadro CX
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro FX 4800
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 230 OEM
2 GB VRAM • 24 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 440 OEM
2 GB VRAM • 43.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 460M
2 GB VRAM • 60 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 470M
2 GB VRAM • 72 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 480
2 GB VRAM • 177.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 580
2 GB VRAM • 192.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 545
2 GB VRAM • 38.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 560M
2 GB VRAM • 60 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 570M
2 GB VRAM • 72 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 580 Rev. 2
2 GB VRAM • 192.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 590
2 GB VRAM • 164 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 640 OEM Rebrand
2 GB VRAM • 38.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 670M
2 GB VRAM • 72 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 760 OEM Rebrand
2 GB VRAM • 179.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 260 OEM
2 GB VRAM • 112.9 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro 4000 Mac Edition
2 GB VRAM • 89.9 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
AMD FireGL V8650
2 GB VRAM • 111 GB/s
AMD
AmazonNeweggeBayPCPartPicker

Find the best GPU for Llama-3.2-1B

Build Hardware for Llama-3.2-1B

Model Card

View on HuggingFace

Read the full model card for detailed information about this model.

▸ SPEC SHEET

Llama-3.2-1B — 1.2B Dense.

▸ SPECIFICATIONS
PARAMETERS
1.2B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
4K tokens
CAPABILITIES
chat
RELEASE DATE
2024-09-25
PROVIDER
Meta
FAMILY
llama
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.891.2 GB94%
Q5_K_S5.571.3 GB96%
Q5_K_M5.71.3 GB96%
Q6_K6.561.5 GB97%
Q8_08.51.8 GB100%
FP16162.9 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO7.6
MATH7.0
IFEval57.0
BBH8.7
GPQA3.4
MUSR3.0
BigCodeBench8.2
Arena Elo1069.0
LiveCodeBench1.9
AIME0.0
MATH-5000.0
GPQA Diamond19.6
HLE5.3
§ 02RUN COMMAND

Run Llama-3.2-1B locally with Ollama — needs 1.2 GB VRAM at Q4_K_M:

$ollama run llama3.2:1.2b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA GeForce GTX 470
1 GB · 133.9 GB/s
NVIDIA GeForce GTX 570
1 GB · 152 GB/s
NVIDIA GeForce GTX 570 Rev. 2
1 GB · 152 GB/s
NVIDIA GeForce GTX 460 v2 ES
1 GB · 128.3 GB/s
NVIDIA GeForce GTX 560 OEM
1 GB · 128.3 GB/s
NVIDIA GeForce GTX 560 Ti 448
1 GB · 152 GB/s
NVIDIA Quadro FX 5600
2 GB · 76.8 GB/s
NVIDIA Quadro FX 5600 Mac Edition
2 GB · 76.8 GB/s
NVIDIA Tesla C870
2 GB · 76.8 GB/s
NVIDIA Tesla D870
2 GB · 76.8 GB/s
NVIDIA Tesla S870
2 GB · 76.8 GB/s
NVIDIA Quadro CX
2 GB · 76.8 GB/s
NVIDIA Quadro FX 4800
2 GB · 76.8 GB/s
NVIDIA GeForce GT 230 OEM
2 GB · 24 GB/s
NVIDIA GeForce GT 440 OEM
2 GB · 43.2 GB/s