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 11 quants, from 28.6 GB (Q2_K) to 83.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
Kolibri 1 Heretic – 78.1B parameter LLM with reasoning and tools support
Kolibri 1 Heretic is a 78.1B parameter model based on the Kolibri‑1 architecture. It supports reasoning and tool usage and is released under Apache‑2.0. The model is a mixture of experts and was quantized by mradermacher.
Good at
- Reasoning tasks
- Tool integration
- Large context handling
Limits
- No vision support
- Requires large VRAM for full precision
- License requires compliance with Apache‑2.0
Best for
- Complex problem solving
- Automated workflow scripting
- Research prototyping
Who it’s for. Developers and researchers needing a large language model with reasoning and tool capabilities. The model is suitable for environments that can accommodate its memory requirements and comply with the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 28.6 GB | 30.0 GB | Too big | Get file → | |
| Q3_K_S | 33.9 GB | 35.2 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 | 42.2 GB | 43.6 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 → | |
| 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 → | |
| Q8_0 | 83.1 GB | 84.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (file size 28.63 GB, estimated memory 30 GB) or Q3_K_S (33.87 GB, 35.2 GB). If 12 GB VRAM is available, Q3_K_M (37.52 GB, 38.9 GB) is a good balance. For 16 GB VRAM, Q4_K_S (44.57 GB, 45.9 GB) offers higher quality while staying within limits.
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: 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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q2_K (28.6 GB file, about 30.0 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.
The Q8_0 file is 83.1 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 Q2_K at 28.6 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 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?
Not at an 8K context. The smallest file needs about 30.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Kolibri 1 Heretic GGUF?
It depends on the quant: Q2_K is 28.6 GB, Q3_K_S is 33.9 GB, Q3_K_M is 37.5 GB, Q3_K_L is 40.6 GB, IQ4_XS is 42.2 GB, Q4_K_S is 44.6 GB and 5 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-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?
The smallest quant, Q2_K, requires about 30 GB of VRAM, so 8 GB is insufficient.
Does the model support image 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.