LL

Small Llama3 6B

LlamaGGUF by ukungUpdated 2024-05-31
Download on Hugging Face
Parameters6.29B
Context8K
Layers24
Architecturellama
Smallest quant2.5 GB
Quick answer

Small Llama3 6B needs about 5.2 GB of memory at Q4_K_M (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 14 quants, from 2.5 GB (Q2_K) to 6.7 GB (Q8_0).

Small Llama3 6B – 6.29B parameter Llama model

Small Llama3 6B is a 6.29B parameter Llama model with a trained context of 8192 tokens. It is available in multiple GGUF quantizations ranging from Q2_K to Q8_0. The model is suitable for local inference with llama.cpp.

Good at

  • Fast inference on low‑memory GPUs
  • Compact model size
  • Versatile quantization options

Limits

  • No vision support
  • License not specified
  • Requires 8k context for full performance

Best for

  • Chatbots on edge devices
  • Rapid prototyping
  • Educational demos

Who it’s for. Developers and researchers needing a lightweight Llama model for local deployment. The model is ideal for those who prefer open‑source quantizations and can manage the 8k token context.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 3.8 GB
Fits Get file →
Q3_K_S2.9 GB 4.2 GB
Fits Get file →
Q3_K_M3.2 GB 4.5 GB
Fits Get file →
Q3_K_L3.4 GB 4.7 GB
Fits Get file →
Q4_03.7 GB 5.0 GB
Fits Get file →
Q4_K_S3.7 GB 5.0 GB
Fits Get file →
Q4_K_M3.9 GB 5.2 GB
Fits Get file →
Q4_14.0 GB 5.3 GB
Fits Get file →
Q5_04.4 GB 5.7 GB
Fits Get file →
Q5_K_S4.4 GB 5.7 GB
Fits Get file →
Q5_K_M4.5 GB 5.8 GB
Fits Get file →
Q5_14.8 GB 6.1 GB
Fits Get file →
Q6_K5.2 GB 6.5 GB
Fits Get file →
Q8_06.7 GB 8.0 GB
Tight Get file →

For 8 GB VRAM, Q4_K_M (est. 5.2 GB) or Q5_K_M (est. 5.8 GB) are suitable. If 6 GB VRAM is available, Q4_K_S (5 GB) or Q4_0 (5 GB) work well. For 4 GB VRAM, Q3_K_S (4.2 GB) or Q3_K_M (4.5 GB) are recommended.

What GPU do you need for Small Llama3 6B?

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 Q2_K (2.5 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_M (4.5 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (6.7 GB file, about 8.0 GB in use).

Which Small Llama3 6B quant should you choose?

Q4_K_M is the usual starting point for Small Llama3 6B: it balances file size and quality well. Here it is a 3.9 GB file.

The Q8_0 file is 6.7 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 2.5 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
Parameters6.29B
Layers24
Trained context8,192 tokens
KV cache (fp16)96 KB per token

Source

Quantized byukung
FamilyLlama
Downloads (HF)676
Last updated2024-05-31

Frequently asked questions about Small Llama3 6B

How much VRAM does Small Llama3 6B need?

About 5.2 GB at Q4_K_M with an 8K context window. That is the 3.9 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 Small Llama3 6B on an 8 GB GPU?

Yes, with Q8_0: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Small Llama3 6B GGUF?

It depends on the quant: Q2_K is 2.5 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.2 GB, Q3_K_L is 3.4 GB, Q4_0 is 3.7 GB, Q4_K_S is 3.7 GB and 8 more.

What context length does Small Llama3 6B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.8 GB at 8K.

Where can I download Small Llama3 6B GGUF?

The files are on Hugging Face in the ukung/Small-Llama3-6B-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 Small Llama3 6B on 8 GB VRAM?

Yes, Q4_K_M or Q5_K_M quantizations fit within 8 GB VRAM, using about 5.2–5.8 GB of memory at 8k context.

What is the smallest quantization that fits 4 GB VRAM?

Q3_K_S uses 4.2 GB and Q3_K_M uses 4.5 GB, both suitable for 4 GB VRAM with 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from ukung

All by ukung →

More Llama models

All Llama →

Other small models

All small models →