TI

TinyMistral 248M Chat v2

TinymistralGGUF by ukungUpdated 2024-05-20
Download on Hugging Face
Parameters248M
Context2K
Layers12
Architecturellama
Smallest quant0.1 GB
Quick answer

TinyMistral 248M Chat v2 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. This repository has 14 quants, from 0.1 GB (Q2_K) to 0.3 GB (Q8_0).

TinyMistral 248M Chat v2 is a 248M-parameter Tinymistral model in GGUF format, quantized by ukung. Its trained context length is 2K tokens. The repository has 14 quant files, from 0.1 GB (Q2_K) to 0.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.6 GB
Fits Get file →
Q3_K_S0.1 GB 0.6 GB
Fits Get file →
Q3_K_M0.1 GB 0.7 GB
Fits Get file →
Q3_K_L0.1 GB 0.7 GB
Fits Get file →
Q4_00.1 GB 0.7 GB
Fits Get file →
Q4_K_S0.1 GB 0.7 GB
Fits Get file →
Q4_K_M0.2 GB 0.7 GB
Fits Get file →
Q4_10.2 GB 0.7 GB
Fits Get file →
Q5_00.2 GB 0.7 GB
Fits Get file →
Q5_K_S0.2 GB 0.7 GB
Fits Get file →
Q5_K_M0.2 GB 0.7 GB
Fits Get file →
Q5_10.2 GB 0.7 GB
Fits Get file →
Q6_K0.2 GB 0.7 GB
Fits Get file →
Q8_00.3 GB 0.8 GB
Fits Get file →

What GPU do you need for TinyMistral 248M Chat v2?

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 Q8_0 (0.3 GB file, about 0.9 GB in use).

Which TinyMistral 248M Chat v2 quant should you choose?

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

The Q8_0 file is 0.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.1 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

Architecturellama
Parameters248M
Layers12
Trained context2,048 tokens
KV cache (fp16)12 KB per token

Source

Quantized byukung
Downloads (HF)7
Last updated2024-05-20

Frequently asked questions about TinyMistral 248M Chat v2

How much VRAM does TinyMistral 248M Chat v2 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 Chat v2 on an 8 GB GPU?

Yes, with Q8_0: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyMistral 248M Chat v2 GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_0 is 0.1 GB, Q4_K_S is 0.1 GB and 8 more.

What context length does TinyMistral 248M Chat v2 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 2K.

Where can I download TinyMistral 248M Chat v2 GGUF?

The files are on Hugging Face in the ukung/TinyMistral-248M-Chat-v2-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 ukung

All by ukung →

More Tinymistral models

All Tinymistral →

Other tiny models

All tiny models →