LL

Dracarys Llama 3.1 70B Instruct

LlamaGGUF by bartowskiUpdated 2024-08-16
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant16.8 GB
Quick answer

Dracarys Llama 3.1 70B Instruct needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 19 quants, from 16.8 GB (IQ1_M) to 75.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Dracarys Llama 3.1 70B Instruct – a fine‑tuned coding model

Dracarys Llama 3.1 70B Instruct is a 70.6B parameter model finetuned from Meta‑Llama‑3.1‑70B‑Instruct. It targets improved coding performance and uses a 131072 token context window. The model is released under the llama3 license.

Good at

  • Coding assistance
  • Instruction following
  • Large context handling

Limits

  • No vision support
  • Requires large VRAM for full quality
  • License restricts commercial use

Best for

  • Developers writing code
  • Researchers testing instruction models
  • Educators creating coding tutorials

Who it’s for. The model is suitable for users who need a high‑capacity language model focused on code generation and instruction compliance. It is ideal for those with sufficient GPU memory to run large quantizations and who comply with the llama3 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M16.8 GB 19.9 GB
Too big Get file →
IQ2_XXS19.1 GB 22.3 GB
Too big Get file →
IQ2_XS21.1 GB 24.3 GB
Too big Get file →
IQ2_M24.1 GB 27.3 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q2_K_L27.4 GB 30.6 GB
Too big Get file →
IQ3_XXS27.5 GB 30.7 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
Q3_K_XL38.1 GB 41.2 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q4_K_L43.3 GB 46.5 GB
Too big Get file →
Q5_K_M49.9 GB (2 parts) 53.1 GB
Too big Get file →
Q6_K57.9 GB (2 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (2 parts) 78.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (16.75 GB file, 19.9 GB memory at 8 k context). For 12 GB VRAM, IQ2_XXS (19.1 GB file, 22.3 GB memory). For 24 GB VRAM, Q4_K_M (42.52 GB file, 45.7 GB memory). Larger quants such as Q8_0 (74.98 GB file, 78.2 GB memory) require combined system RAM and GPU VRAM.

What GPU do you need for Dracarys Llama 3.1 70B 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_L (43.3 GB file, about 46.5 GB in use).

Which Dracarys Llama 3.1 70B Instruct quant should you choose?

Q4_K_M is the usual starting point for Dracarys Llama 3.1 70B Instruct: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 75.0 GB, about 1.8 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 IQ1_M at 16.8 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
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bybartowski
FamilyLlama
Licensellama3
Downloads (HF)1,020
Last updated2024-08-16

Frequently asked questions about Dracarys Llama 3.1 70B Instruct

How much VRAM does Dracarys Llama 3.1 70B Instruct need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Dracarys Llama 3.1 70B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dracarys Llama 3.1 70B Instruct GGUF?

It depends on the quant: IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_M is 24.1 GB, Q2_K is 26.4 GB, Q2_K_L is 27.4 GB and 13 more.

What context length does Dracarys Llama 3.1 70B Instruct support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Dracarys Llama 3.1 70B Instruct GGUF?

The files are on Hugging Face in the bartowski/Dracarys-Llama-3.1-70B-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 Dracarys Llama 3.1 70B Instruct use?

Hugging Face lists the license as llama3. 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 Dracarys Llama 3.1 70B Instruct on 8 GB VRAM?

Use the IQ1_M quant, which has a 16.75 GB file and requires about 19.9 GB of memory at 8 k context.

What is the largest quant that fits in 24 GB VRAM?

The Q4_K_M quant has a 42.52 GB file and needs about 45.7 GB of memory, so it will not fit; a smaller quant such as IQ2_XXS is recommended.

Does the model support image input?

No, the model has no vision capabilities.

Other GGUFs of Dracarys-Llama-3.1-70B-Instruct

Similar models

Browse all →

More from bartowski

All by bartowski →

More Llama models

All Llama →

Other large models

All large models →