KO

Kolibri 1

KolibriGGUF by Harsha001Updated 2026-10-24
Download on Hugging Face
Parameters78.1B
Context256K
Layers50
Architecturekolibri1
Smallest quant41.7 GB
Quick answer

Kolibri 1 needs about 43.1 GB of memory at Q4_0 (a 41.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 41.7 GB (Q4_0) to 80.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

Kolibri 1 is a 78.1B-parameter Kolibri model in GGUF format, quantized by Harsha001. Its trained context length is 256K tokens. The repository has 4 quant files, from 41.7 GB (Q4_0) to 80.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_041.7 GB 43.0 GB
Too big Get file →
Q4_041.8 GB 43.1 GB
Too big Get file →
Q6_K64.7 GB 66.1 GB
Too big Get file →
Q8_080.7 GB 82.0 GB
Too big Get file →

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 Q4_0 (41.8 GB file, about 43.1 GB in use).

Which Kolibri 1 quant should you choose?

Q4_0 (41.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_0 at 41.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturekolibri1
Parameters78.1B (approximate, mixture of experts)
Layers50
Trained context262,144 tokens
KV cache (fp16)100 KB per token

Source

Quantized byHarsha001
FamilyKolibri
Licenseapache-2.0
Downloads (HF)164
Last updated2026-10-24

Frequently asked questions about Kolibri 1

How much VRAM does Kolibri 1 need?

About 43.1 GB at Q4_0 with an 8K context window. That is the 41.8 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 43.0 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: Q4_0 is 41.7 GB, Q4_0 is 41.8 GB, Q6_K is 64.7 GB, Q8_0 is 80.7 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 Harsha001/Kolibri-1-ROCmFPX 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.

Other GGUFs of Kolibri-1-BF16

Similar models

Browse all →

More from Harsha001

All by Harsha001 →

More Kolibri models

All Kolibri →

Other large models

All large models →