DO

Donnager 70B V1A

DonnagerGGUF by bartowskiUpdated 2024-09-14
Download on Hugging Face
Parameters69B
Context32K
Layers80
Architecturellama
Smallest quant15.9 GB
Quick answer

Donnager 70B V1A needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 18 quants, from 15.9 GB (IQ1_M) to 73.3 GB (Q8_0).

Donnager 70B V1A – 70B parameter LLaMA model in GGUF format

Donnager 70B V1A is a 69‑billion parameter LLaMA model quantized for llama.cpp. It supports chat templates such as Metharme, Text Completion, Mistral, Alpaca, and Vicuna. The model is available in multiple quantizations ranging from IQ1_M to Q8_0.

Good at

  • Large context handling
  • High‑capacity language modeling
  • Versatile chat template support

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is other

Best for

  • Research on large language models
  • Fine‑tuning for specialized domains
  • Benchmarking quantization methods

Who it’s for. Researchers and developers who need a large LLaMA‑based model for experimentation or fine‑tuning. The model is suitable for users with sufficient GPU memory to run the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M15.9 GB 19.1 GB
Too big Get file →
IQ2_XXS18.3 GB 21.5 GB
Too big Get file →
IQ2_XS20.3 GB 23.5 GB
Too big Get file →
IQ2_M23.2 GB 26.4 GB
Too big Get file →
Q2_K25.5 GB 28.6 GB
Too big Get file →
Q2_K_L25.7 GB 28.9 GB
Too big Get file →
IQ3_XXS26.6 GB 29.8 GB
Too big Get file →
Q3_K_S29.9 GB 33.1 GB
Too big Get file →
IQ3_M30.9 GB 34.1 GB
Too big Get file →
Q3_K_M33.3 GB 36.5 GB
Too big Get file →
Q3_K_L36.1 GB 39.3 GB
Too big Get file →
Q3_K_XL36.4 GB 39.6 GB
Too big Get file →
IQ4_XS36.8 GB 40.0 GB
Too big Get file →
Q4_039.0 GB 42.2 GB
Too big Get file →
Q4_K_M41.4 GB 44.6 GB
Too big Get file →
Q5_K_M48.8 GB 51.9 GB
Too big Get file →
Q6_K56.6 GB (2 parts) 59.8 GB
Too big Get file →
Q8_073.3 GB (2 parts) 76.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (15.94 GB file, 19.1 GB memory at 8k context). For 16 GB VRAM, IQ2_M (23.23 GB file, 26.4 GB memory) or Q2_K (25.46 GB file, 28.6 GB memory). For 24 GB VRAM, Q3_K_M (33.27 GB file, 36.5 GB memory) or Q4_K_M (41.42 GB file, 44.6 GB memory). Memory estimates are approximate.

What GPU do you need for Donnager 70B V1A?

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_XS (20.3 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (26.6 GB file, about 29.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which Donnager 70B V1A quant should you choose?

Q4_K_M is the usual starting point for Donnager 70B V1A: it balances file size and quality well. Here it is a 41.4 GB file.

The Q8_0 file is 73.3 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 15.9 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
Parameters69B
Layers80
Trained context32,764 tokens
KV cache (fp16)320 KB per token

Source

Quantized bybartowski
FamilyDonnager
Licenseother
Downloads (HF)779
Last updated2024-09-14

Frequently asked questions about Donnager 70B V1A

How much VRAM does Donnager 70B V1A need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 Donnager 70B V1A on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Donnager 70B V1A GGUF?

It depends on the quant: IQ1_M is 15.9 GB, IQ2_XXS is 18.3 GB, IQ2_XS is 20.3 GB, IQ2_M is 23.2 GB, Q2_K is 25.5 GB, Q2_K_L is 25.7 GB and 12 more.

What context length does Donnager 70B V1A support?

The GGUF header lists a trained context length of 32,764 tokens (32K). 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 Donnager 70B V1A GGUF?

The files are on Hugging Face in the bartowski/Donnager-70B-v1-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 Donnager 70B V1A use?

Hugging Face lists the license as other. 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 Donnager 70B V1A on 8 GB VRAM?

Use the IQ1_M quantization; it requires about 19.1 GB of memory at 8k context, which exceeds 8 GB VRAM, so it will not fit entirely on GPU.

Which quantization gives the best balance of size and performance?

IQ2_M offers a moderate file size of 23.23 GB and memory usage of 26.4 GB, suitable for mid‑range GPUs.

Does this model support system prompts?

No, the model does not support a system prompt according to the prompt format documentation.

Other GGUFs of Donnager-70B-v1

Similar models

Browse all →

More from bartowski

All by bartowski →

More Donnager models

All Donnager →

Other large models

All large models →