KO

Kohlibri 40B

KohlibriGGUF by mradermacherUpdated 2026-10-21
Download on Hugging Face
Parameters40.3B
Context256K
Layers50
Architecturekolibri1
Smallest quant14.9 GB
Quick answer

Kohlibri 40B needs about 25.8 GB of memory at Q4_K_M (a 24.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 7 quants, from 14.9 GB (Q2_K) to 24.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

Kohlibri 40B is a 40.3B-parameter Kohlibri model in GGUF format, quantized by mradermacher. Its trained context length is 256K tokens. The repository has 7 quant files, from 14.9 GB (Q2_K) to 24.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K14.9 GB 16.2 GB
Too big Get file →
Q3_K_S17.6 GB 18.9 GB
Too big Get file →
Q3_K_M19.4 GB 20.8 GB
Too big Get file →
Q3_K_L21.0 GB 22.4 GB
Too big Get file →
IQ4_XS21.9 GB 23.2 GB
Too big Get file →
Q4_K_S23.1 GB 24.4 GB
Too big Get file →
Q4_K_M24.5 GB 25.8 GB
Too big Get file →

What GPU do you need for Kohlibri 40B?

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: the best quant that fits is IQ4_XS (21.9 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (24.5 GB file, about 25.8 GB in use).

Which Kohlibri 40B quant should you choose?

Q4_K_M is the usual starting point for Kohlibri 40B: it balances file size and quality well. Here it is a 24.5 GB file.

If memory is tight, the smallest file is Q2_K at 14.9 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

Architecturekolibri1
Parameters40.3B (approximate, mixture of experts)
Layers50
Trained context262,144 tokens
KV cache (fp16)100 KB per token

Source

Quantized bymradermacher
FamilyKohlibri
Licenseapache-2.0
Downloads (HF)568
Last updated2026-10-21

Frequently asked questions about Kohlibri 40B

How much VRAM does Kohlibri 40B need?

About 25.8 GB at Q4_K_M with an 8K context window. That is the 24.5 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 Kohlibri 40B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kohlibri 40B GGUF?

It depends on the quant: Q2_K is 14.9 GB, Q3_K_S is 17.6 GB, Q3_K_M is 19.4 GB, Q3_K_L is 21.0 GB, IQ4_XS is 21.9 GB, Q4_K_S is 23.1 GB and 1 more.

What context length does Kohlibri 40B 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 Kohlibri 40B GGUF?

The files are on Hugging Face in the mradermacher/Kohlibri-40B-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 Kohlibri 40B 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 Kohlibri-40B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kohlibri models

All Kohlibri →

Other large models

All large models →