MI

KimLan mistral 0.5b 40k

MistralGGUF by elliotthwangmsaUpdated 2024-01-03
Download on Hugging Face
Parameters588M
Context4K
Layers32
Architecturellama
Smallest quant0.4 GB
Quick answer

KimLan mistral 0.5b 40k needs about 2.0 GB of memory at Q5_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q5_K_M) to 0.6 GB (Q8_0).

KimLan mistral 0.5b 40k is a 588M-parameter Mistral model in GGUF format, quantized by elliotthwangmsa. Its trained context length is 4K tokens. The repository has 2 quant files, from 0.4 GB (Q5_K_M) to 0.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M0.4 GB 1.5 GB
Fits Get file →
Q8_00.6 GB 1.7 GB
Fits Get file →

What GPU do you need for KimLan mistral 0.5b 40k?

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 (0.6 GB file, about 2.2 GB in use).

Which KimLan mistral 0.5b 40k quant should you choose?

Q5_K_M (0.4 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters588M
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized byelliotthwangmsa
FamilyMistral
Downloads (HF)23
Last updated2024-01-03

Frequently asked questions about KimLan mistral 0.5b 40k

How much VRAM does KimLan mistral 0.5b 40k need?

About 2.0 GB at Q5_K_M with an 8K context window. That is the 0.4 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 KimLan mistral 0.5b 40k on an 8 GB GPU?

Yes, with Q8_0: the 0.6 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of KimLan mistral 0.5b 40k GGUF?

It depends on the quant: Q5_K_M is 0.4 GB, Q8_0 is 0.6 GB.

What context length does KimLan mistral 0.5b 40k support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download KimLan mistral 0.5b 40k GGUF?

The files are on Hugging Face in the elliotthwangmsa/KimLan_mistral-0.5b-40k-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 elliotthwangmsa

All by elliotthwangmsa →

More Mistral models

All Mistral →

Other tiny models

All tiny models →