LL

Llama 3.1 8B

LlamaGGUF by mradermacherUpdated 2024-10-11
Download on Hugging Face
Parameters8B
Context128K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

Llama 3.1 8B needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 3.2 GB (Q2_K) to 16.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Llama 3.1 8B fine‑tuned on MagPie Ultra

Llama 3.1 8B is a fine‑tuned model on the argilla-warehouse/magpie-ultra-v1.0 dataset. It is available in multiple GGUF quantizations and supports a context length of 131072 tokens.

Good at

  • Fine‑tuned on MagPie Ultra
  • Large context support
  • Multiple quant options

Limits

  • No vision support
  • License: llama3.1
  • No mixture of experts

Best for

  • Chat applications
  • Text generation
  • Research prototyping

Who it’s for. Developers and researchers who need a compact LLM with a large context window and fine‑tuned performance on the MagPie Ultra dataset. The model is suitable for local deployment via llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.5 GB 6.1 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
F1616.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.92 GB, estimated 6.5 GB memory). For 12 GB VRAM, Q5_K_M (file size 5.73 GB, estimated 7.3 GB memory) is a good balance. For 16 GB VRAM, Q6_K (file size 6.6 GB, estimated 8.2 GB memory) provides higher precision.

What GPU do you need for Llama 3.1 8B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_L (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 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 Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which Llama 3.1 8B quant should you choose?

Q4_K_M is the usual starting point for Llama 3.1 8B: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 GB, about 1.7 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 Q2_K at 3.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama3.1
Downloads (HF)1,226
Last updated2024-10-11

Frequently asked questions about Llama 3.1 8B

How much VRAM does Llama 3.1 8B need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 3.1 8B on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.1 8B GGUF?

It depends on the quant: Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, IQ3_S is 3.7 GB, IQ3_M is 3.8 GB, Q3_K_M is 4.0 GB and 9 more.

What context length does Llama 3.1 8B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Llama 3.1 8B GGUF?

The files are on Hugging Face in the mradermacher/Llama-3.1-8B-MagPie-Ultra-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 3.1 8B use?

Hugging Face lists the license as llama3.1. 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 3.1 8B on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 6.5 GB of VRAM at 8 k context, which fits within an 8 GB budget.

What is the smallest quant available?

The smallest quant is Q2_K, 3.18 GB file size, using about 4.8 GB of VRAM at 8 k context.

Does this model support vision tasks?

No, the model does not include vision capabilities.

Other GGUFs of Llama-3.1-8B-MagPie-Ultra

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →