Kolibri 1 Heretic needs about 48.8 GB of memory at Q4_K_M (a 47.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.9 GB to 64.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
Kolibri 1 Heretic – 78 billion‑parameter reasoning model
Kolibri 1 Heretic is a 78 billion‑parameter model based on the Kolibri‑1 architecture. It supports large context lengths of 262,144 tokens and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.
Good at
- Large context reasoning
- High‑parameter capacity
- Apache‑2.0 licensed
Limits
- No vision support
- Requires large VRAM for full precision
- Limited to 262,144 token context
Best for
- Complex reasoning tasks
- Long‑form content generation
- Research prototyping
Who it’s for. Developers and researchers needing a large‑parameter reasoning model with extensive context. The model is suitable for environments that can handle its memory requirements and for users who comply with the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.9 GB | 2.2 GB | Fits | Get file → | |
| IQ1_S | 15.9 GB | 17.3 GB | Too big | Get file → | |
| IQ1_M | 17.7 GB | 19.0 GB | Too big | Get file → | |
| IQ2_XXS | 20.6 GB | 22.0 GB | Too big | Get file → | |
| IQ2_XS | 23.0 GB | 24.3 GB | Too big | Get file → | |
| IQ2_S | 23.3 GB | 24.6 GB | Too big | Get file → | |
| IQ2_M | 25.6 GB | 27.0 GB | Too big | Get file → | |
| Q2_K_S | 26.7 GB | 28.0 GB | Too big | Get file → | |
| Q2_K | 28.6 GB | 30.0 GB | Too big | Get file → | |
| IQ3_XXS | 30.2 GB | 31.5 GB | Too big | Get file → | |
| IQ3_XS | 32.1 GB | 33.4 GB | Too big | Get file → | |
| Q3_K_S | 33.9 GB | 35.2 GB | Too big | Get file → | |
| IQ3_S | 33.9 GB | 35.2 GB | Too big | Get file → | |
| IQ3_M | 34.4 GB | 35.7 GB | Too big | Get file → | |
| Q3_K_M | 37.5 GB | 38.9 GB | Too big | Get file → | |
| Q3_K_L | 40.6 GB | 41.9 GB | Too big | Get file → | |
| IQ4_XS | 41.8 GB | 43.1 GB | Too big | Get file → | |
| Q4_0 | 44.4 GB | 45.7 GB | Too big | Get file → | |
| Q4_K_S | 44.6 GB | 45.9 GB | Too big | Get file → | |
| Q4_K_M | 47.5 GB | 48.8 GB | Too big | Get file → | |
| Q4_1 | 49.1 GB | 50.4 GB | Too big | Get file → | |
| Q5_K_S | 53.9 GB | 55.2 GB | Too big | Get file → | |
| Q5_K_M | 55.6 GB | 56.9 GB | Too big | Get file → | |
| Q6_K | 64.2 GB | 65.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 15.93 GB, estimated 17.3 GB memory). For 16 GB VRAM, IQ2_M (file size 25.63 GB, estimated 27 GB memory) or Q2_K (file size 28.63 GB, estimated 30 GB memory). For 32 GB VRAM, Q4_K_M (file size 47.45 GB, estimated 48.8 GB memory) or Q5_K_S (file size 53.91 GB, estimated 55.2 GB memory).
What GPU do you need for Kolibri 1 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 (0.9 GB file, about 2.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.9 GB file, about 2.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.9 GB file, about 2.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.9 GB file, about 2.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.9 GB file, about 2.2 GB in use).
- 24 GB VRAM: the best quant that fits is IQ2_XXS (20.6 GB file, about 22.0 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_XXS (30.2 GB file, about 31.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_S (44.6 GB file, about 45.9 GB in use).
Which Kolibri 1 Heretic quant should you choose?
Q4_K_M is the usual starting point for Kolibri 1 Heretic: it balances file size and quality well. Here it is a 47.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.9 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 Kolibri 1 Heretic
How much VRAM does Kolibri 1 Heretic need?
About 48.8 GB at Q4_K_M with an 8K context window. That is the 47.5 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 Kolibri 1 Heretic on an 8 GB GPU?
Yes, with the smaller files: the 0.9 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Kolibri 1 Heretic GGUF?
It depends on the quant: file is 0.9 GB, IQ1_S is 15.9 GB, IQ1_M is 17.7 GB, IQ2_XXS is 20.6 GB, IQ2_XS is 23.0 GB, IQ2_S is 23.3 GB and 18 more.
What context length does Kolibri 1 Heretic support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.4 GB at 32K.
Where can I download Kolibri 1 Heretic GGUF?
The files are on Hugging Face in the mradermacher/Kolibri-1-heretic-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 Kolibri 1 Heretic 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 Kolibri 1 Heretic on 8 GB VRAM?
Use the IQ1_S quant, which estimates 17.3 GB memory at 8 k context. It will likely need more VRAM than 8 GB, so consider a lower‑precision quant or a larger GPU.
Does the model support vision inputs?
No, Kolibri 1 Heretic does not have vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.