Chaifighter 20B v3 i1 needs about 15.1 GB of memory at Q4_K_M (a 11.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 4.2 GB (IQ1_S) to 16.0 GB (Q6_K).
Chaifighter 20B v3 i1 – 19.5B llama model with 8K context
Chaifighter 20B v3 i1 is a 19.5B parameter llama model. It supports a native context length of 4096 tokens and can be extended to 16384 with RoPE scaling. The model is released under the apache-2.0 license.
Good at
- Roleplay
- Long‑form dialogue
- Custom prompt templates
Limits
- No vision support
- Requires 8K context for full performance
- Large VRAM needed for higher quants
Best for
- Chatbots with extended context
- Interactive storytelling
- Custom prompt engineering
Who it’s for. Developers building chat applications that need a large language model with extended context. The model is suitable for users who can manage the VRAM requirements and want a flexible quantization strategy.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.2 GB | 6.2 GB | Fits | Get file → | |
| IQ1_M | 4.6 GB | 6.6 GB | Fits | Get file → | |
| IQ2_XXS | 5.2 GB | 7.2 GB | Tight | Get file → | |
| IQ2_XS | 5.8 GB | 7.8 GB | Tight | Get file → | |
| IQ2_S | 6.1 GB | 8.1 GB | Too big | Get file → | |
| IQ2_M | 6.6 GB | 8.6 GB | Too big | Get file → | |
| Q2_K | 7.2 GB | 9.2 GB | Too big | Get file → | |
| IQ3_XXS | 7.5 GB | 9.5 GB | Too big | Get file → | |
| IQ3_XS | 8.0 GB | 10.0 GB | Too big | Get file → | |
| Q3_K_S | 8.4 GB | 10.4 GB | Too big | Get file → | |
| IQ3_S | 8.5 GB | 10.4 GB | Too big | Get file → | |
| IQ3_M | 8.7 GB | 10.7 GB | Too big | Get file → | |
| Q3_K_M | 9.4 GB | 11.4 GB | Too big | Get file → | |
| Q3_K_L | 10.2 GB | 12.2 GB | Too big | Get file → | |
| IQ4_XS | 10.4 GB | 12.4 GB | Too big | Get file → | |
| Q4_0 | 11.0 GB | 13.0 GB | Too big | Get file → | |
| Q4_K_S | 11.1 GB | 13.0 GB | Too big | Get file → | |
| Q4_K_M | 11.7 GB | 13.7 GB | Too big | Get file → | |
| Q5_K_S | 13.4 GB | 15.4 GB | Too big | Get file → | |
| Q5_K_M | 13.8 GB | 15.7 GB | Too big | Get file → | |
| Q6_K | 16.0 GB | 17.9 GB | Too big | Get file → |
For 8‑10 GB VRAM, use IQ1_S (4.2 GB, 7.7 GB memory) or IQ1_M (4.59 GB, 8 GB memory). For 12‑15 GB VRAM, IQ2_S (6.1 GB, 9.6 GB memory) or Q4_K_S (11.06 GB, 14.5 GB memory) are suitable. Higher quants like Q5_K_M (13.76 GB, 17.2 GB memory) require 18 GB or more VRAM.
What GPU do you need for Chaifighter 20B v3 i1?
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: the best quant that fits is IQ1_M (4.6 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_S (8.5 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (11.7 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (16.0 GB file, about 19.4 GB in use).
Which Chaifighter 20B v3 i1 quant should you choose?
Q4_K_M is the usual starting point for Chaifighter 20B v3 i1: it balances file size and quality well. Here it is a 11.7 GB file.
If memory is tight, the smallest file is IQ1_S at 4.2 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
Source
Frequently asked questions about Chaifighter 20B v3 i1
How much VRAM does Chaifighter 20B v3 i1 need?
About 15.1 GB at Q4_K_M with an 8K context window. That is the 11.7 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 v3 i1 on an 8 GB GPU?
Yes, with IQ1_M: the 4.6 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Chaifighter 20B v3 i1 GGUF?
It depends on the quant: IQ1_S is 4.2 GB, IQ1_M is 4.6 GB, IQ2_XXS is 5.2 GB, IQ2_XS is 5.8 GB, IQ2_S is 6.1 GB, IQ2_M is 6.6 GB and 15 more.
What context length does Chaifighter 20B v3 i1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.0 GB at 8K and 1.5 GB at 4K.
Where can I download Chaifighter 20B v3 i1 GGUF?
The files are on Hugging Face in the mradermacher/Chaifighter-20B-v3-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 v3 i1 use?
Hugging Face lists the license as apache-2.0. 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 Chaifighter 20B v3 i1 on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quants will fit within 8 GB VRAM, with estimated memory usage of 7.7 GB and 8 GB respectively.
Does the model support image inputs?
No, Chaifighter 20B v3 i1 has no vision capabilities.
What is the maximum context length I can use?
The native context length is 4096 tokens; it can be extended to 16384 tokens with RoPE scaling.