CR

Crunchy onion

CrunchyGGUF by EpiculousUpdated 2024-01-25
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant17.3 GB
Quick answer

Crunchy onion needs about 30.0 GB of memory at Q4_K_M (a 28.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 12 quants, from 17.3 GB (Q2_K) to 49.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Crunchy onion – a 46.7B llama-based MLP model

Crunchy onion is a 46.7B parameter llama architecture model trained on Mixtral base and LimaRP data. It uses a 32768 token context window and is released under agpl-3.0. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Mixtral-based instruction following
  • High parameter count

Limits

  • No vision support
  • agpl-3.0 license restricts commercial use
  • Requires 8k context for memory estimates

Best for

  • Research on instruction fine‑tuning
  • Educational demos of large language models
  • Testing quantization trade‑offs

Who it’s for. Researchers and developers who need a large llama‑style model with extensive context and are comfortable with an agpl-3.0 license. The model is suitable for experimentation and academic projects.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K17.3 GB 18.9 GB
Too big Get file →
Q3_K_S20.4 GB 22.0 GB
Too big Get file →
Q3_K_M22.5 GB 24.1 GB
Too big Get file →
Q3_K_L24.2 GB 25.7 GB
Too big Get file →
Q4_026.4 GB 28.0 GB
Too big Get file →
Q4_K_S26.7 GB 28.3 GB
Too big Get file →
Q4_K_M28.4 GB 30.0 GB
Too big Get file →
Q5_032.2 GB 33.8 GB
Too big Get file →
Q5_K_S32.2 GB 33.8 GB
Too big Get file →
Q5_K_M33.2 GB 34.8 GB
Too big Get file →
Q6_K38.4 GB 40.0 GB
Too big Get file →
Q8_049.6 GB 51.2 GB
Too big Get file →

For 8 GB VRAM, Q4_0 or Q4_K_S are recommended, each needing about 28 GB of memory at 8k context. If you have 16 GB VRAM, Q5_K_M or Q6_K provide a balance between size and performance. Larger quants like Q8_0 require over 50 GB memory and are best for high‑end setups.

What GPU do you need for Crunchy onion?

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 Q3_K_S (20.4 GB file, about 22.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (28.4 GB file, about 30.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).

Which Crunchy onion quant should you choose?

Q4_K_M is the usual starting point for Crunchy onion: it balances file size and quality well. Here it is a 28.4 GB file.

The Q8_0 file is 49.6 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 17.3 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
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byEpiculous
FamilyCrunchy
Licenseagpl-3.0
Downloads (HF)671
Last updated2024-01-25

Frequently asked questions about Crunchy onion

How much VRAM does Crunchy onion need?

About 30.0 GB at Q4_K_M with an 8K context window. That is the 28.4 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 Crunchy onion on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Crunchy onion GGUF?

It depends on the quant: Q2_K is 17.3 GB, Q3_K_S is 20.4 GB, Q3_K_M is 22.5 GB, Q3_K_L is 24.2 GB, Q4_0 is 26.4 GB, Q4_K_S is 26.7 GB and 6 more.

What context length does Crunchy onion support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Crunchy onion GGUF?

The files are on Hugging Face in the Epiculous/Crunchy-onion-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 Crunchy onion use?

Hugging Face lists the license as agpl-3.0. 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 Crunchy onion on 8 GB VRAM?

No, the smallest quant requires about 18.9 GB memory at 8k context, exceeding 8 GB VRAM.

Does Crunchy onion support vision tasks?

No, the model has no vision capabilities.

Is Crunchy onion suitable for commercial use?

No, it is licensed under agpl-3.0, which restricts commercial deployment.

Similar models

Browse all →

More from Epiculous

All by Epiculous →

More Crunchy models

All Crunchy →

Other large models

All large models →