CH

Chaifighter 20B

ChaifighterGGUF by mradermacherUpdated 2024-12-13
Download on Hugging Face
Parameters20.8B
Context4K
Layers94
Architecturellama
Smallest quant4.5 GB
Quick answer

Chaifighter 20B needs about 16.1 GB of memory at Q4_K_M (a 12.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 4.5 GB (IQ1_S) to 17.0 GB (Q6_K).

Chaifighter 20B is a 20.8B-parameter Chaifighter model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 22 quant files, from 4.5 GB (IQ1_S) to 17.0 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.5 GB 6.5 GB
Fits Get file →
IQ1_M4.9 GB 7.0 GB
Fits Get file →
IQ2_XXS5.6 GB 7.7 GB
Tight Get file →
IQ2_XS6.2 GB 8.3 GB
Too big Get file →
IQ2_S6.5 GB 8.6 GB
Too big Get file →
IQ2_M7.1 GB 9.1 GB
Too big Get file →
Q2_K_S7.1 GB 9.2 GB
Too big Get file →
Q2_K7.7 GB 9.8 GB
Too big Get file →
IQ3_XXS8.0 GB 10.1 GB
Too big Get file →
IQ3_XS8.5 GB 10.6 GB
Too big Get file →
Q3_K_S9.0 GB 11.1 GB
Too big Get file →
IQ3_S9.0 GB 11.1 GB
Too big Get file →
IQ3_M9.3 GB 11.4 GB
Too big Get file →
Q3_K_M10.0 GB 12.1 GB
Too big Get file →
Q3_K_L10.9 GB 13.0 GB
Too big Get file →
IQ4_XS11.1 GB 13.2 GB
Too big Get file →
Q4_011.8 GB 13.8 GB
Too big Get file →
Q4_K_S11.8 GB 13.9 GB
Too big Get file →
Q4_K_M12.5 GB 14.5 GB
Too big Get file →
Q5_K_S14.3 GB 16.4 GB
Too big Get file →
Q5_K_M14.7 GB 16.8 GB
Too big Get file →
Q6_K17.0 GB 19.1 GB
Too big Get file →

What GPU do you need for Chaifighter 20B?

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: the best quant that fits is IQ3_XXS (8.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (11.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.0 GB file, about 20.7 GB in use).

Which Chaifighter 20B quant should you choose?

Q4_K_M is the usual starting point for Chaifighter 20B: it balances file size and quality well. Here it is a 12.5 GB file.

If memory is tight, the smallest file is IQ1_S at 4.5 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
Parameters20.8B
Layers94
Trained context4,096 tokens
KV cache (fp16)376 KB per token

Source

Quantized bymradermacher
Licensecc-by-4.0
Downloads (HF)346
Last updated2024-12-13

Frequently asked questions about Chaifighter 20B

How much VRAM does Chaifighter 20B need?

About 16.1 GB at Q4_K_M with an 8K context window. That is the 12.5 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 Chaifighter 20B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Chaifighter 20B GGUF?

It depends on the quant: IQ1_S is 4.5 GB, IQ1_M is 4.9 GB, IQ2_XXS is 5.6 GB, IQ2_XS is 6.2 GB, IQ2_S is 6.5 GB, IQ2_M is 7.1 GB and 16 more.

What context length does Chaifighter 20B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download Chaifighter 20B GGUF?

The files are on Hugging Face in the mradermacher/Chaifighter-20B-i1-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 Chaifighter 20B use?

Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Chaifighter-20B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Chaifighter models

All Chaifighter →

Other medium models

All medium models →