Veiled Calla 4B needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.1 GB (IQ1_S) to 3.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Veiled Calla 4B – a role‑play focused gemma3 model
Veiled Calla 4B is a 3.88 billion‑parameter gemma3 model optimized for atmospheric role‑play. It supports 131072 context tokens and is released under apache‑2.0. The model is available in a range of GGUF quantizations.
Good at
- Atmospheric role‑play
- Consistent character portrayal
- Narrative mystery
Limits
- No vision support
- Uncensored only in role‑play mode
- Requires system prompt in assistant mode
Best for
- Interactive storytelling
- Character‑driven dialogues
- Creative writing prompts
Who it’s for. Developers and hobbyists looking for a lightweight role‑play model. It is suitable for local deployment with GGUF and llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.1 GB | 2.8 GB | Fits | Get file → | |
| IQ1_M | 1.2 GB | 2.8 GB | Fits | Get file → | |
| IQ2_XXS | 1.3 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XS | 1.4 GB | 3.0 GB | Fits | Get file → | |
| IQ2_S | 1.4 GB | 3.1 GB | Fits | Get file → | |
| IQ2_M | 1.5 GB | 3.2 GB | Fits | Get file → | |
| Q2_K_S | 1.6 GB | 3.3 GB | Fits | Get file → | |
| IQ3_XXS | 1.7 GB | 3.3 GB | Fits | Get file → | |
| Q2_K | 1.7 GB | 3.4 GB | Fits | Get file → | |
| IQ3_XS | 1.9 GB | 3.5 GB | Fits | Get file → | |
| IQ3_S | 1.9 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 1.9 GB | 3.6 GB | Fits | Get file → | |
| IQ3_M | 2.0 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_L | 2.2 GB | 3.9 GB | Fits | Get file → | |
| IQ4_XS | 2.3 GB | 3.9 GB | Fits | Get file → | |
| IQ4_NL | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q5_K_S | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q6_K | 3.2 GB | 4.8 GB | Fits | Get file → |
For 8 GB VRAM, use IQ4_NL (2.36 GB) or Q4_0 (2.37 GB). If 12 GB VRAM is available, Q4_K_M (2.49 GB) or Q5_K_M (2.83 GB) provide higher quality. For 16 GB VRAM, Q6_K (3.19 GB) offers the best trade‑off.
What GPU do you need for Veiled Calla 4B?
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: the best quant that fits is Q4_K_S (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.2 GB file, about 4.8 GB in use).
Which Veiled Calla 4B quant should you choose?
Q4_K_M is the usual starting point for Veiled Calla 4B: it balances file size and quality well. Here it is a 2.5 GB file.
If memory is tight, the smallest file is IQ1_S at 1.1 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
Source
Frequently asked questions about Veiled Calla 4B
How much VRAM does Veiled Calla 4B need?
About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Veiled Calla 4B on an 8 GB GPU?
Yes, with Q6_K: the 3.2 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Veiled Calla 4B GGUF?
It depends on the quant: IQ1_S is 1.1 GB, IQ1_M is 1.2 GB, IQ2_XXS is 1.3 GB, IQ2_XS is 1.4 GB, IQ2_S is 1.4 GB, IQ2_M is 1.5 GB and 18 more.
What context length does Veiled Calla 4B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download Veiled Calla 4B GGUF?
The files are on Hugging Face in the mradermacher/Veiled-Calla-4B-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 Veiled Calla 4B 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 Veiled Calla 4B on 8 GB VRAM?
Yes, use IQ4_NL or Q4_0 quantizations, which are around 2.4 GB each. The estimated memory at 8k context is about 4 GB.
Does this model support vision?
No, it is a text‑only model. Vision files are not provided.
Is the model uncensored?
It is uncensored in role‑play mode but refuses in assistant mode without a system prompt.