HI

openaccess-ai-collective_hippogriff-30b-chat

HippogriffGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters32.5B
Context2K
Layers60
Architecturellama
Smallest quant13.5 GB
Quick answer

openaccess-ai-collective_hippogriff-30b-chat needs about 33.2 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 13.5 GB (Q2_K) to 34.6 GB (Q8_0).

Hippogriff 30B Chat – a 32.5B‑parameter Llama‑style chat model

Hippogriff 30B Chat is a 32.5B‑parameter Llama‑based model fine‑tuned on a variety of instruction, role‑play, and Q&A datasets. It is available in GGUF format and supports chat‑only prompting with USER: and ASSISTANT: tokens.

Good at

  • Chat‑only instruction following
  • In‑context QA
  • Prose generation

Limits

  • No vision support
  • Limited math handling
  • Requires large VRAM for full precision

Best for

  • Local chat assistants
  • Storytelling with role‑play
  • In‑context question answering

Who it’s for. Developers and researchers who need a large chat model for local inference. The model is suitable for users with access to GPUs that can handle 30B‑parameter models or who can use quantised versions for lower VRAM usage.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.5 GB 17.3 GB
Too big Get file →
Q3_K_S14.1 GB 17.8 GB
Too big Get file →
Q3_K_M15.8 GB 19.5 GB
Too big Get file →
Q3_K_L17.3 GB 21.1 GB
Too big Get file →
Q4_018.4 GB 22.1 GB
Too big Get file →
Q4_K_S18.4 GB 22.2 GB
Too big Get file →
Q4_K_M19.6 GB 23.4 GB
Too big Get file →
Q5_022.4 GB 26.2 GB
Too big Get file →
Q5_K_S22.4 GB 26.2 GB
Too big Get file →
Q5_K_M23.0 GB 26.8 GB
Too big Get file →
Q6_K26.7 GB 30.5 GB
Too big Get file →
Q8_034.6 GB 38.3 GB
Too big Get file →

For 8 GB VRAM use Q4_K_S (18.44 GB file, ~32 GB memory). For 12 GB VRAM use Q4_K_M (19.62 GB file, ~33.2 GB memory). For 16 GB VRAM use Q5_K_M (23.05 GB file, ~36.6 GB memory). Memory estimates are approximate.

What GPU do you need for openaccess-ai-collective_hippogriff-30b-chat?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q4_K_S (18.4 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 40.3 GB in use).

Which openaccess-ai-collective_hippogriff-30b-chat quant should you choose?

Q4_K_M is the usual starting point for openaccess-ai-collective_hippogriff-30b-chat: it balances file size and quality well. Here it is a 19.6 GB file.

The Q8_0 file is 34.6 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 Q2_K at 13.5 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
Parameters32.5B
Layers60
Trained context2,048 tokens
KV cache (fp16)1560 KB per token

Source

Quantized byTheBloke
Licenseother
Downloads (HF)2,209
Last updated2023-09-27

Frequently asked questions about openaccess-ai-collective_hippogriff-30b-chat

How much VRAM does openaccess-ai-collective_hippogriff-30b-chat need?

About 33.2 GB at Q4_K_M with an 8K context window. That is the 19.6 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 openaccess-ai-collective_hippogriff-30b-chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of openaccess-ai-collective_hippogriff-30b-chat GGUF?

It depends on the quant: Q2_K is 13.5 GB, Q3_K_S is 14.1 GB, Q3_K_M is 15.8 GB, Q3_K_L is 17.3 GB, Q4_0 is 18.4 GB, Q4_K_S is 18.4 GB and 6 more.

What context length does openaccess-ai-collective_hippogriff-30b-chat support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 13.1 GB at 8K and 3.3 GB at 2K.

Where can I download openaccess-ai-collective_hippogriff-30b-chat GGUF?

The files are on Hugging Face in the TheBloke/hippogriff-30b-chat-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 openaccess-ai-collective_hippogriff-30b-chat 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 Hippogriff 30B Chat on 8 GB VRAM?

Use the Q4_K_S quantised model; it requires about 32 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient for full inference.

Does the model support vision or image input?

No, the model has no vision capability and only processes text.

What is the context length of the model?

The model was trained with a context length of 2048 tokens.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

Other medium models

All medium models →