MI

OpenMia Indo Mistral 7b v4

MistralGGUF by indischepartijUpdated 2024-02-07
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant0.6 GB
Quick answer

OpenMia Indo Mistral 7b v4 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 0.6 GB (Q5_K_M) to 4.4 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

OpenMia Indo Mistral 7b v4 is a 7.24B-parameter Mistral model in GGUF format, quantized by indischepartij. Its trained context length is 32K tokens. The repository has 2 quant files, from 0.6 GB (Q5_K_M) to 4.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M0.6 GB 2.1 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →

What GPU do you need for OpenMia Indo Mistral 7b v4?

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 Q5_K_M (0.6 GB file, about 2.1 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).

Which OpenMia Indo Mistral 7b v4 quant should you choose?

Q4_K_M is the usual starting point for OpenMia Indo Mistral 7b v4: it balances file size and quality well. Here it is a 4.4 GB file.

If memory is tight, the smallest file is Q5_K_M at 0.6 GB, with the quality trade-offs that come with fewer bits. 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byindischepartij
FamilyMistral
Downloads (HF)25
Last updated2024-02-07

Frequently asked questions about OpenMia Indo Mistral 7b v4

How much VRAM does OpenMia Indo Mistral 7b v4 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 OpenMia Indo Mistral 7b v4 on an 8 GB GPU?

Yes, with Q4_K_M: the 4.4 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of OpenMia Indo Mistral 7b v4 GGUF?

It depends on the quant: Q5_K_M is 0.6 GB, Q4_K_M is 4.4 GB.

What context length does OpenMia Indo Mistral 7b v4 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 OpenMia Indo Mistral 7b v4 GGUF?

The files are on Hugging Face in the indischepartij/OpenMia-Indo-Mistral-7b-v4-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 indischepartij

All by indischepartij →

More Mistral models

All Mistral →

Other small models

All small models →