LL

Llama-3.3-8B-Instruct

LlamaGGUF by MungertUpdated 2025-12-30
Download on Hugging Face
Parameters8B
Context8K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

Llama-3.3-8B-Instruct needs about 6.8 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 26 quants, from 0.0 GB to 16.1 GB (BF16).

Llama‑3.3‑8B‑Instruct – 8 B parameter instruction model

Llama‑3.3‑8B‑Instruct is an 8 B parameter instruction‑tuned model from the Llama family. It was quantized by Mungert and released in GGUF format. The model supports a 8192‑token context window.

Good at

  • Instruction following
  • Chat‑style dialogue
  • Code generation

Limits

  • No vision support
  • Requires 8 k context for estimates
  • License: llama3.3

Best for

  • Building lightweight chatbots
  • Fine‑tuning on small datasets
  • Rapid prototyping of LLM apps

Who it’s for. Developers and researchers who need a small, instruction‑tuned Llama model for local inference. The model is suitable for edge deployments and quick experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ2_XXS2.8 GB 4.3 GB
Fits Get file →
IQ2_XS3.0 GB 4.5 GB
Fits Get file →
IQ2_S3.1 GB 4.6 GB
Fits Get file →
Q2_K_S3.1 GB 4.7 GB
Fits Get file →
IQ2_M3.2 GB 4.8 GB
Fits Get file →
Q2_K_M3.3 GB 4.8 GB
Fits Get file →
IQ3_XXS3.7 GB 5.2 GB
Fits Get file →
IQ3_XS3.8 GB 5.3 GB
Fits Get file →
Q3_K_S4.1 GB 5.6 GB
Fits Get file →
IQ3_M4.1 GB 5.7 GB
Fits Get file →
Q3_K_M4.2 GB 5.8 GB
Fits Get file →
IQ4_NL4.5 GB 6.1 GB
Fits Get file →
IQ4_XS4.6 GB 6.2 GB
Fits Get file →
Q4_K_S4.9 GB 6.5 GB
Fits Get file →
Q4_05.1 GB 6.6 GB
Fits Get file →
Q4_15.1 GB 6.7 GB
Fits Get file →
Q4_K_M5.3 GB 6.8 GB
Fits Get file →
Q5_05.9 GB 7.5 GB
Tight Get file →
Q5_K_M6.1 GB 7.6 GB
Tight Get file →
Q5_16.4 GB 7.9 GB
Tight Get file →
Q6_K_M6.9 GB 8.4 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
BF1611.9 GB 13.5 GB
Too big Get file →
F1611.9 GB 13.5 GB
Too big Get file →
BF1616.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (2.77 GB, 4.3 GB memory) or Q2_K_S (3.13 GB, 4.7 GB memory). For 12 GB VRAM, Q4_0 (5.05 GB, 6.6 GB memory) or Q5_0 (5.92 GB, 7.5 GB memory) provide a good balance of size and performance. Larger VRAM allows higher‑precision quants like Q6_K_M (6.85 GB, 8.4 GB memory).

What GPU do you need for Llama-3.3-8B-Instruct?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.2 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (6.4 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (11.9 GB file, about 13.5 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 17.6 GB in use).

Which Llama-3.3-8B-Instruct quant should you choose?

Q4_K_M is the usual starting point for Llama-3.3-8B-Instruct: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 8.5 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMungert
FamilyLlama
Licensellama3.3
Downloads (HF)2,181
Last updated2025-12-30

Frequently asked questions about Llama-3.3-8B-Instruct

How much VRAM does Llama-3.3-8B-Instruct need?

About 6.8 GB at Q4_K_M with an 8K context window. That is the 5.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Llama-3.3-8B-Instruct on an 8 GB GPU?

Yes, with Q5_1: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama-3.3-8B-Instruct GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XXS is 2.8 GB, IQ2_XS is 3.0 GB, IQ2_S is 3.1 GB, Q2_K_S is 3.1 GB, IQ2_M is 3.2 GB and 20 more.

What context length does Llama-3.3-8B-Instruct support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Llama-3.3-8B-Instruct GGUF?

The files are on Hugging Face in the Mungert/Llama-3.3-8B-Instruct-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Llama-3.3-8B-Instruct use?

Hugging Face lists the license as llama3.3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Llama‑3.3‑8B‑Instruct on 8 GB VRAM?

Yes, using IQ2_XXS or Q2_K_S quants keeps VRAM usage under 8 GB.

Does this model support image inputs?

No, it has no vision capabilities.

What license does it use?

The model is licensed under llama3.3.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Llama models

All Llama →

Other small models

All small models →