MI

Minitron 8B Instruct 200K

MistralGGUF by prithivMLmodsUpdated 2024-11-08
Download on Hugging Face
Parameters8.41B
Context8K
Layers40
Architecturellama
Smallest quant5.1 GB
Quick answer

Minitron 8B Instruct 200K needs about 7.0 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 5.1 GB (Q4_K_M) to 16.8 GB (F16).

Minitron 8B Instruct 200K is a 8.41B-parameter Mistral model in GGUF format, quantized by prithivMLmods. Its trained context length is 8K tokens. The repository has 4 quant files, from 5.1 GB (Q4_K_M) to 16.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.1 GB 7.0 GB
Fits Get file →
Q5_K_M6.0 GB 7.8 GB
Tight Get file →
Q8_08.9 GB 10.8 GB
Too big Get file →
F1616.8 GB 18.7 GB
Too big Get file →

What GPU do you need for Minitron 8B Instruct 200K?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.0 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.8 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.8 GB file, about 18.7 GB in use).

Which Minitron 8B Instruct 200K quant should you choose?

Q4_K_M is the usual starting point for Minitron 8B Instruct 200K: it balances file size and quality well. Here it is a 5.1 GB file.

The Q8_0 file is 8.9 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.41B
Layers40
Trained context8,192 tokens
KV cache (fp16)160 KB per token

Source

Quantized byprithivMLmods
FamilyMistral
Downloads (HF)64
Last updated2024-11-08

Frequently asked questions about Minitron 8B Instruct 200K

How much VRAM does Minitron 8B Instruct 200K need?

About 7.0 GB at Q4_K_M with an 8K context window. That is the 5.1 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 Minitron 8B Instruct 200K on an 8 GB GPU?

Yes, with Q5_K_M: the 6.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Minitron 8B Instruct 200K GGUF?

It depends on the quant: Q4_K_M is 5.1 GB, Q5_K_M is 6.0 GB, Q8_0 is 8.9 GB, F16 is 16.8 GB.

What context length does Minitron 8B Instruct 200K support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.3 GB at 8K and 1.3 GB at 8K.

Where can I download Minitron 8B Instruct 200K GGUF?

The files are on Hugging Face in the prithivMLmods/Minitron-8B-Instruct-200K-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 Minitron 8B Instruct 200K use?

Hugging Face lists the license as creativeml-openrail-m. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Mistral-NeMo-Minitron-8B-Instruct

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Mistral models

All Mistral →

Other small models

All small models →