Theia 21B v1 needs about 15.2 GB of memory at Q4_K_M (a 12.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 20 quants, from 7.2 GB (IQ2_M) to 81.7 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.
Theia 21B v1 – a 20.4B llama model finetuned for rich prose
Theia 21B v1 is a 20.4B parameter llama model, finetuned from Steelskull's NeMoria 21B. It includes completion, roleplay, and instruction training, yielding improved storytelling and richer prose. The model supports a 1,024,000 token context window.
Good at
- Enhanced roleplay
- Rich storytelling
- Instruction following
Limits
- Large context requires high VRAM
- No vision capabilities
- License is other
Best for
- Creative writing
- Dialogue generation
- Narrative assistance
Who it’s for. Users looking for a large, text‑centric model with strong roleplay and storytelling abilities. It is suitable for developers and writers who can provide sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 7.2 GB | 10.0 GB | Too big | Get file → | |
| Q2_K | 7.8 GB | 10.6 GB | Too big | Get file → | |
| Q2_K_L | 8.5 GB | 11.3 GB | Too big | Get file → | |
| IQ3_XS | 8.6 GB | 11.5 GB | Too big | Get file → | |
| Q3_K_S | 9.0 GB | 11.9 GB | Too big | Get file → | |
| IQ3_M | 9.4 GB | 12.2 GB | Too big | Get file → | |
| Q3_K_M | 10.0 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_L | 10.8 GB | 13.7 GB | Too big | Get file → | |
| IQ4_XS | 11.1 GB | 14.0 GB | Too big | Get file → | |
| Q3_K_XL | 11.4 GB | 14.3 GB | Too big | Get file → | |
| Q4_K_S | 11.7 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_M | 12.4 GB | 15.2 GB | Too big | Get file → | |
| Q4_K_L | 12.9 GB | 15.7 GB | Too big | Get file → | |
| Q5_K_S | 14.1 GB | 17.0 GB | Too big | Get file → | |
| Q5_K_M | 14.5 GB | 17.3 GB | Too big | Get file → | |
| Q5_K_L | 14.9 GB | 17.8 GB | Too big | Get file → | |
| Q6_K | 16.8 GB | 19.6 GB | Too big | Get file → | |
| Q6_K_L | 17.1 GB | 19.9 GB | Too big | Get file → | |
| Q8_0 | 21.7 GB | 24.6 GB | Too big | Get file → | |
| F32 | 81.7 GB (3 parts) | 84.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (12.36 GB file, ~15.2 GB memory at 8k context). For 12 GB VRAM, Q4_K_L (12.86 GB file, ~15.7 GB memory). For 24 GB VRAM, Q8_0 (21.71 GB file, ~24.6 GB memory).
What GPU do you need for Theia 21B v1?
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 Q3_K_S (9.0 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_L (12.9 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K_L (17.1 GB file, about 19.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (21.7 GB file, about 24.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (21.7 GB file, about 24.6 GB in use).
Which Theia 21B v1 quant should you choose?
Q4_K_M is the usual starting point for Theia 21B v1: it balances file size and quality well. Here it is a 12.4 GB file.
The Q8_0 file is 21.7 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 IQ2_M at 7.2 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 Theia 21B v1
How much VRAM does Theia 21B v1 need?
About 15.2 GB at Q4_K_M with an 8K context window. That is the 12.4 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 Theia 21B v1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Theia 21B v1 GGUF?
It depends on the quant: IQ2_M is 7.2 GB, Q2_K is 7.8 GB, Q2_K_L is 8.5 GB, IQ3_XS is 8.6 GB, Q3_K_S is 9.0 GB, IQ3_M is 9.4 GB and 14 more.
What context length does Theia 21B v1 support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.4 GB at 32K.
Where can I download Theia 21B v1 GGUF?
The files are on Hugging Face in the bartowski/Theia-21B-v1-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 Theia 21B v1 use?
Hugging Face lists the license as other. 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 Theia 21B v1 on 8 GB VRAM?
Use the Q4_K_M quant, which requires about 15.2 GB memory at 8k context. It will not fit entirely on 8 GB VRAM, so you need at least 16 GB VRAM.
Does Theia 21B v1 support vision tasks?
No, the model has no vision capabilities.
What is the maximum context length of Theia 21B v1?
The model supports 1,024,000 tokens of context.