BO

bot3 Q6 K

BotGGUF by minchyeomUpdated 2025-01-24
Download on Hugging Face
Parameters1.92B
Context128K
Layers31
Architectureqwen2
Smallest quant1.6 GB
Quick answer

bot3 Q6 K needs about 2.3 GB of memory at Q6_K (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.0 GB.

bot3 Q6 K is a 1.92B-parameter Bot model in GGUF format, quantized by minchyeom. Its trained context length is 128K tokens. The repository has 1 quant file, from 1.6 GB (Q6_K) to 1.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K1.6 GB 2.3 GB
Fits Get file →

What GPU do you need for bot3 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: the best quant that fits is Q6_K (1.6 GB file, about 2.3 GB in use).

Which bot3 Q6 K quant should you choose?

Q6_K (1.6 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

Architectureqwen2
Parameters1.92B
Layers31
Trained context131,072 tokens
KV cache (fp16)31 KB per token

Source

Quantized byminchyeom
FamilyBot
Base modelminchyeom/bot3
Downloads (HF)11
Last updated2025-01-24

Frequently asked questions about bot3 Q6 K

How much VRAM does bot3 Q6 K need?

About 2.3 GB at Q6_K with an 8K context window. That is the 1.6 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 bot3 Q6 K on an 8 GB GPU?

Yes, with Q6_K: the 1.6 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of bot3 Q6 K GGUF?

It depends on the quant: Q6_K is 1.6 GB.

What context length does bot3 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 0.3 GB at 8K and 1.0 GB at 32K.

Where can I download bot3 Q6 K GGUF?

The files are on Hugging Face in the minchyeom/bot3-Q6_K-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from minchyeom

All by minchyeom →

More Bot models

All Bot →

Other tiny models

All tiny models →