KO

Kolibri 1

KolibriGGUF by InsidiousFiddlerUpdated 2026-10-04
Download on Hugging Face
Parameters78B
Context256K
Layers50
Architecturekolibri1
Smallest quant37.5 GB
Quick answer

Kolibri 1 needs about 56.9 GB of memory at Q5_K_XL (a 55.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 37.5 GB (Q3_K_XL) to 83.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

Kolibri 1 – a large mixture‑of‑experts model for German and English reasoning

Kolibri 1 is a 78.10‑billion‑parameter mixture‑of‑experts model. It is optimized for long‑context inference and explicit reasoning. The model supports German and English text input and output.

Good at

  • Long‑context reasoning
  • Tool‑calling
  • Structured extraction

Limits

  • Requires experimental Kolibri patch for llama.cpp
  • Full model must stay in memory
  • No vision support

Best for

  • Document‑processing workflows
  • Agentic tool‑calling systems
  • Multi‑step reasoning tasks

Who it’s for. Developers building conversational assistants or internal knowledge systems that need German and English reasoning. The model is intended for use with a human reviewer before any action is taken.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_XL37.5 GB 38.8 GB
Too big Get file →
Q4_K_XL47.4 GB 48.8 GB
Too big Get file →
Q5_K_XL55.6 GB 56.9 GB
Too big Get file →
Q6_K_XL64.2 GB 65.5 GB
Too big Get file →
Q8_083.1 GB 84.5 GB
Too big Get file →

For 8 GB VRAM use Q3_K_XL (file size 37.51 GB, memory 38.8 GB). For 12 GB VRAM use Q4_K_XL (47.44 GB, 48.8 GB). For 16 GB VRAM use Q5_K_XL (55.57 GB, 56.9 GB). Memory estimates are approximate.

What GPU do you need for Kolibri 1?

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q3_K_XL (37.5 GB file, about 38.8 GB in use).

Which Kolibri 1 quant should you choose?

Q5_K_XL (55.6 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q3_K_XL at 37.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturekolibri1
Parameters78B (approximate, mixture of experts)
Layers50
Trained context262,144 tokens
KV cache (fp16)100 KB per token

Source

Quantized byInsidiousFiddler
FamilyKolibri
Licenseapache-2.0
Downloads (HF)3,111
Last updated2026-10-04

Frequently asked questions about Kolibri 1

How much VRAM does Kolibri 1 need?

About 56.9 GB at Q5_K_XL with an 8K context window. That is the 55.6 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 38.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kolibri 1 GGUF?

It depends on the quant: Q3_K_XL is 37.5 GB, Q4_K_XL is 47.4 GB, Q5_K_XL is 55.6 GB, Q6_K_XL is 64.2 GB, Q8_0 is 83.1 GB.

What context length does Kolibri 1 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 GGUF?

The files are on Hugging Face in the InsidiousFiddler/Kolibri-1-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 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 on 8 GB VRAM?

Use the Q3_K_XL quantization; it requires about 38.8 GB of memory at 8 k context, so 8 GB VRAM is insufficient.

Does Kolibri 1 support vision tasks?

No, Kolibri 1 is a text‑only model.

What license applies to Kolibri 1?

Apache‑2.0 licensed weights and configuration.

Other GGUFs of Kolibri-1-BF16

Similar models

Browse all →

More Kolibri models

All Kolibri →

Other large models

All large models →