Rocinante XL 16B v1 Heretic needs about 12.1 GB of memory at Q4_K_M (a 9.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 0.0 GB to 13.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.2 GB.
Rocinante XL 16B v1 Heretic – 16.1B llama model with tool use
Rocinante XL 16B v1 Heretic is a 16.1B parameter llama model. It supports tool usage and was trained on a 131072 token context. The model is available in multiple GGUF quantizations.
Good at
- Tool integration
- Large context handling
- High parameter count
Limits
- No vision support
- License not specified
- Requires large VRAM for full precision
Best for
- Chatbot with tool calls
- Complex reasoning tasks
- Custom prompt engineering
Who it’s for. Developers and researchers needing a large llama model with tool support. Suitable for building advanced conversational agents or AI assistants that require extended context.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.3 GB | Fits | Get file → | |
| IQ1_S | 3.8 GB | 6.1 GB | Fits | Get file → | |
| IQ1_M | 4.1 GB | 6.4 GB | Fits | Get file → | |
| IQ2_XXS | 4.6 GB | 6.9 GB | Fits | Get file → | |
| IQ2_XS | 5.0 GB | 7.4 GB | Tight | Get file → | |
| IQ2_S | 5.3 GB | 7.6 GB | Tight | Get file → | |
| IQ2_M | 5.7 GB | 8.0 GB | Too big | Get file → | |
| Q2_K_S | 5.8 GB | 8.1 GB | Too big | Get file → | |
| Q2_K | 6.2 GB | 8.5 GB | Too big | Get file → | |
| IQ3_XXS | 6.4 GB | 8.7 GB | Too big | Get file → | |
| IQ3_XS | 6.9 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_S | 7.2 GB | 9.5 GB | Too big | Get file → | |
| IQ3_S | 7.2 GB | 9.5 GB | Too big | Get file → | |
| IQ3_M | 7.4 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_M | 7.9 GB | 10.2 GB | Too big | Get file → | |
| Q3_K_L | 8.6 GB | 10.9 GB | Too big | Get file → | |
| IQ4_XS | 8.8 GB | 11.1 GB | Too big | Get file → | |
| Q4_0 | 9.2 GB | 11.6 GB | Too big | Get file → | |
| IQ4_NL | 9.3 GB | 11.6 GB | Too big | Get file → | |
| Q4_K_S | 9.3 GB | 11.6 GB | Too big | Get file → | |
| Q4_K_M | 9.7 GB | 12.1 GB | Too big | Get file → | |
| Q4_1 | 10.2 GB | 12.5 GB | Too big | Get file → | |
| Q5_K_S | 11.1 GB | 13.5 GB | Too big | Get file → | |
| Q5_K_M | 11.4 GB | 13.7 GB | Too big | Get file → | |
| Q6_K | 13.2 GB | 15.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (6.1 GB memory) or Q2_K (8.5 GB memory). For 12 GB VRAM, Q4_K_M (12.1 GB memory) or Q5_K_S (13.5 GB memory) are suitable. Larger VRAM allows higher quality quants such as Q6_K (15.5 GB memory).
What GPU do you need for Rocinante XL 16B v1 Heretic?
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 the main file (0.0 GB file, about 2.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.3 GB in use).
- 8 GB VRAM: the best quant that fits is IQ2_M (5.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_S (9.3 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (13.2 GB file, about 15.5 GB in use).
Which Rocinante XL 16B v1 Heretic quant should you choose?
Q4_K_M is the usual starting point for Rocinante XL 16B v1 Heretic: it balances file size and quality well. Here it is a 9.7 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Rocinante XL 16B v1 Heretic
How much VRAM does Rocinante XL 16B v1 Heretic need?
About 12.1 GB at Q4_K_M with an 8K context window. That is the 9.7 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 Rocinante XL 16B v1 Heretic on an 8 GB GPU?
Yes, with IQ2_M: the 5.7 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 Rocinante XL 16B v1 Heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.8 GB, IQ1_M is 4.1 GB, IQ2_XXS is 4.6 GB, IQ2_XS is 5.0 GB, IQ2_S is 5.3 GB and 19 more.
What context length does Rocinante XL 16B v1 Heretic support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.8 GB at 8K and 7.2 GB at 32K.
Where can I download Rocinante XL 16B v1 Heretic GGUF?
The files are on Hugging Face in the mradermacher/Rocinante-XL-16B-v1-heretic-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, using IQ1_S or Q2_K quants which estimate 6.1 GB or 8.5 GB memory at 8k context.
Does the model support vision?
No, the model has no vision capability.
What is the context length?
The model was trained on 131072 token context.