LL

Llama 3 Smaug 8B

LlamaGGUF by MaziyarPanahiUpdated 2024-04-20
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

Llama 3 Smaug 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 10 quants, from 3.2 GB (Q2_K) to 8.5 GB (Q8_0).

Llama 3 Smaug 8B – 8.03B parameter model in GGUF format

Llama 3 Smaug 8B is a 8.03B parameter model fine‑tuned from Meta‑Llama‑3‑8B‑Instruct using the Smaug recipe. It supports a 8192 token context window and is available in multiple GGUF quantizations. The model is released by Abacus.AI and can be used with llama.cpp and other GGUF‑compatible clients.

Good at

  • Fast inference on GPUs
  • Low‑memory quantizations
  • Large context support

Limits

  • No vision capabilities
  • License not specified
  • No mixture of experts

Best for

  • Local chatbot deployments
  • Script generation
  • Rapid prototyping

Who it’s for. Developers and researchers who need a compact 8B Llama 3 variant for local inference. The model is suitable for users with limited GPU memory who still require a large context window.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.8 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 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 →
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 →

For 8 GB VRAM, use Q4_K_M (file size 4.92 GB, estimated 6.5 GB memory at 8k context). If 12 GB VRAM is available, Q5_K_M (5.73 GB, 7.3 GB memory) offers higher quality. For maximum quality on 16 GB VRAM, Q8_0 (8.54 GB, 10.1 GB memory) is recommended.

What GPU do you need for Llama 3 Smaug 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).

Which Llama 3 Smaug 8B quant should you choose?

Q4_K_M is the usual starting point for Llama 3 Smaug 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
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMaziyarPanahi
FamilyLlama
Downloads (HF)681
Last updated2024-04-20

Frequently asked questions about Llama 3 Smaug 8B

How much VRAM does Llama 3 Smaug 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 Smaug 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 Smaug 8B GGUF?

It depends on the quant: Q2_K is 3.2 GB, Q3_K_S is 3.7 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, Q4_K_S is 4.7 GB, Q4_K_M is 4.9 GB and 4 more.

What context length does Llama 3 Smaug 8B 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 Smaug 8B GGUF?

The files are on Hugging Face in the MaziyarPanahi/Llama-3-Smaug-8B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Llama 3 Smaug 8B on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 6.5 GB of VRAM at 8k context, which fits within an 8 GB GPU.

Which quantization gives the best quality?

The Q8_0 quantization provides the highest quality but needs 10.1 GB of VRAM at 8k context.

Is this model suitable for multi‑turn conversations?

Yes, it was trained with an 8192 token context window, making it well suited for extended dialogues.

Other GGUFs of Llama-3-Smaug-8B

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Llama models

All Llama →

Other small models

All small models →