TI

TinyMistral 248M v2.5 Q4 K M

TinymistralGGUF by BasedBotsUpdated 2024-04-23
Download on Hugging Face
Parameters248M
Context32K
Layers12
Architecturellama
Smallest quant0.2 GB
Quick answer

TinyMistral 248M v2.5 Q4 K M needs about 0.8 GB of memory at Q4_K_M (a 0.2 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 0.4 GB.

TinyMistral 248M v2.5 Q4 K M is a 248M-parameter Tinymistral model in GGUF format, quantized by BasedBots. Its trained context length is 32K tokens. The repository has 1 quant file, from 0.2 GB (Q4_K_M) to 0.2 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.2 GB 0.8 GB
Fits Get file →

What GPU do you need for TinyMistral 248M v2.5 Q4 K M?

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 Q4_K_M (0.2 GB file, about 0.8 GB in use).

Which TinyMistral 248M v2.5 Q4 K M quant should you choose?

Q4_K_M is the usual starting point for TinyMistral 248M v2.5 Q4 K M: it balances file size and quality well. Here it is a 0.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters248M
Layers12
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized byBasedBots
Licenseapache-2.0
Downloads (HF)4
Last updated2024-04-23

Frequently asked questions about TinyMistral 248M v2.5 Q4 K M

How much VRAM does TinyMistral 248M v2.5 Q4 K M need?

About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.2 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 TinyMistral 248M v2.5 Q4 K M on an 8 GB GPU?

Yes, with Q4_K_M: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyMistral 248M v2.5 Q4 K M GGUF?

It depends on the quant: Q4_K_M is 0.2 GB.

What context length does TinyMistral 248M v2.5 Q4 K M support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download TinyMistral 248M v2.5 Q4 K M GGUF?

The files are on Hugging Face in the BasedBots/TinyMistral-248M-v2.5-Q4_K_M-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 TinyMistral 248M v2.5 Q4 K M 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.

Similar models

Browse all →

More from BasedBots

All by BasedBots →

More Tinymistral models

All Tinymistral →

Other tiny models

All tiny models →