KO

Kosmos EVAA immersive mix v45.1 8B Q6 K

KosmosGGUF by MrDevolverUpdated 2025-02-17
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant6.6 GB
Quick answer

Kosmos EVAA immersive mix v45.1 8B Q6 K needs about 8.2 GB of memory at Q6_K (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Kosmos EVAA immersive mix v45.1 8B Q6 K is a 8.03B-parameter Kosmos model in GGUF format, quantized by MrDevolver. Its trained context length is 128K tokens. The repository has 1 quant file, from 6.6 GB (Q6_K) to 6.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K6.6 GB 8.2 GB
Too big Get file →

What GPU do you need for Kosmos EVAA immersive mix v45.1 8B Q6 K?

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: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).

Which Kosmos EVAA immersive mix v45.1 8B Q6 K quant should you choose?

Q6_K (6.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMrDevolver
FamilyKosmos
Downloads (HF)12
Last updated2025-02-17

Frequently asked questions about Kosmos EVAA immersive mix v45.1 8B Q6 K

How much VRAM does Kosmos EVAA immersive mix v45.1 8B Q6 K need?

About 8.2 GB at Q6_K with an 8K context window. That is the 6.6 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 Kosmos EVAA immersive mix v45.1 8B Q6 K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kosmos EVAA immersive mix v45.1 8B Q6 K GGUF?

It depends on the quant: Q6_K is 6.6 GB.

What context length does Kosmos EVAA immersive mix v45.1 8B Q6 K support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Kosmos EVAA immersive mix v45.1 8B Q6 K GGUF?

The files are on Hugging Face in the MrDevolver/Kosmos-EVAA-immersive-mix-v45.1-8B-Q6_K-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Kosmos-EVAA-immersive-mix-v45.1-8B

Similar models

Browse all →

More from MrDevolver

All by MrDevolver →

More Kosmos models

All Kosmos →

Other small models

All small models →