MI

ministral 3b it q4 k m chunked

MistralGGUF by BoscoTheDogUpdated 2024-11-03
Download on Hugging Face
Parameters3.32B
Context128K
Layers14
Architecturellama
Smallest quant2.0 GB
Quick answer

ministral 3b it q4 k m chunked needs about 3.0 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.0 GB (Q4_K_M) to 2.0 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

ministral 3b it q4 k m chunked is a 3.32B-parameter Mistral model in GGUF format, quantized by BoscoTheDog. Its trained context length is 128K tokens. The repository has 2 quant files, from 2.0 GB (Q4_K_M) to 2.0 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.0 GB 3.0 GB
Fits Get file →
Q4_K_M2.0 GB (16 parts) 3.0 GB
Fits Get file →

What GPU do you need for ministral 3b it q4 k m chunked?

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 (2.0 GB file, about 3.0 GB in use).

Which ministral 3b it q4 k m chunked quant should you choose?

Q4_K_M is the usual starting point for ministral 3b it q4 k m chunked: it balances file size and quality well. Here it is a 2.0 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.32B
Layers14
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byBoscoTheDog
FamilyMistral
Licenseapache-2.0
Downloads (HF)38
Last updated2024-11-03

Frequently asked questions about ministral 3b it q4 k m chunked

How much VRAM does ministral 3b it q4 k m chunked need?

About 3.0 GB at Q4_K_M with an 8K context window. That is the 2.0 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 ministral 3b it q4 k m chunked on an 8 GB GPU?

Yes, with Q4_K_M: the 2.0 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ministral 3b it q4 k m chunked GGUF?

It depends on the quant: Q4_K_M is 2.0 GB, Q4_K_M is 2.0 GB.

What context length does ministral 3b it q4 k m chunked support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download ministral 3b it q4 k m chunked GGUF?

The files are on Hugging Face in the BoscoTheDog/ministral_3b_it_q4_k_m_chunked repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ministral 3b it q4 k m chunked 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 BoscoTheDog

All by BoscoTheDog →

More Mistral models

All Mistral →

Other tiny models

All tiny models →