BA

Bacchus-22B

BacchusGGUF by mradermacherUpdated 2024-06-13
Download on Hugging Face
Parameters21.8B
Context4K
Layers40
Architecturellama
Smallest quant8.1 GB
Quick answer

Bacchus-22B needs about 22.4 GB of memory at Q4_K_M (a 13.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 8.1 GB (Q2_K) to 23.2 GB (Q8_0).

Bacchus‑22B – a 21.8B parameter Llama‑style model

Bacchus‑22B is a 21.8B parameter Llama architecture model trained on 4096 token context. It is available in multiple GGUF quantizations ranging from Q2_K to Q8_0. The model is noted for unpredictable behavior and occasional adult content.

Good at

  • Instruct style prompting
  • General purpose dialogue
  • Role‑playing with Alpaca format

Limits

  • Unpredictable content, may produce adult material
  • No vision support
  • License not specified

Best for

  • Chatbot prototypes
  • Text generation experiments
  • Role‑playing scripts

Who it’s for. Developers and researchers who need a large Llama‑style model for text generation and are comfortable handling potential content issues. The model is suitable for local deployment with GGUF support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.1 GB 13.0 GB
Too big Get file →
IQ3_XS9.0 GB 13.8 GB
Too big Get file →
IQ3_S9.5 GB 14.3 GB
Too big Get file →
Q3_K_S9.5 GB 14.3 GB
Too big Get file →
IQ3_M10.0 GB 14.9 GB
Too big Get file →
Q3_K_M10.6 GB 15.5 GB
Too big Get file →
Q3_K_L11.6 GB 16.5 GB
Too big Get file →
IQ4_XS11.8 GB 16.6 GB
Too big Get file →
Q4_K_S12.4 GB 17.3 GB
Too big Get file →
Q4_K_M13.2 GB 18.0 GB
Too big Get file →
Q5_K_S15.0 GB 19.9 GB
Too big Get file →
Q5_K_M15.5 GB 20.3 GB
Too big Get file →
Q6_K17.9 GB 22.8 GB
Too big Get file →
Q8_023.2 GB 28.1 GB
Too big Get file →

For 8 GB VRAM use Q2_K (8.11 GB, 17.3 GB RAM). For 12 GB VRAM use Q4_K_S (12.43 GB, 21.7 GB RAM). For 16 GB VRAM use Q5_K_M (15.47 GB, 24.7 GB RAM). Estimates are approximate.

What GPU do you need for Bacchus-22B?

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 Q4_K_M (13.2 GB file, about 22.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (17.9 GB file, about 27.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (23.2 GB file, about 32.4 GB in use).

Which Bacchus-22B quant should you choose?

Q4_K_M is the usual starting point for Bacchus-22B: it balances file size and quality well. Here it is a 13.2 GB file.

The Q8_0 file is 23.2 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 8.1 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
Parameters21.8B
Layers40
Trained context4,096 tokens
KV cache (fp16)1040 KB per token

Source

Quantized bymradermacher
FamilyBacchus
Downloads (HF)1,327
Last updated2024-06-13

Frequently asked questions about Bacchus-22B

How much VRAM does Bacchus-22B need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 13.2 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 Bacchus-22B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Bacchus-22B GGUF?

It depends on the quant: Q2_K is 8.1 GB, IQ3_XS is 9.0 GB, IQ3_S is 9.5 GB, Q3_K_S is 9.5 GB, IQ3_M is 10.0 GB, Q3_K_M is 10.6 GB and 8 more.

What context length does Bacchus-22B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 8.7 GB at 8K and 4.4 GB at 4K.

Where can I download Bacchus-22B GGUF?

The files are on Hugging Face in the mradermacher/Bacchus-22B-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 Bacchus‑22B on 8 GB VRAM?

Yes, use the Q2_K quant which is 8.11 GB and requires about 17.3 GB of RAM.

Does Bacchus‑22B support vision?

No, the model has no vision capabilities.

What is the context length of Bacchus‑22B?

The trained context length is 4096 tokens.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other medium models

All medium models →