BU

BUT FIT_csmpt7b

ButGGUF by BUT-FITUpdated 2025-05-21
Download on Hugging Face
Parameters6.7B
Context2K
Layers32
Architecturempt
Smallest quant7.1 GB
Quick answer

BUT FIT_csmpt7b needs about 18.2 GB of memory at BF16 (a 13.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 7.1 GB (Q8_0) to 26.8 GB (F32).

6.7B Czech language model for coding tasks

BUT FIT_csmpt7b is a 6.7B parameter MPT architecture model trained on Czech data. It supports coding and was pretrained on 272b tokens from English MPT7b. The model is released under Apache‑2.0.

Good at

  • Czech language understanding
  • Coding assistance
  • Large context handling

Limits

  • No vision support
  • Requires 8k context for estimates
  • License is Apache‑2.0

Best for

  • Developers building Czech coding assistants
  • Researchers testing Czech LLMs
  • Educational tools for Czech programming

Who it’s for. The model is suitable for developers and researchers working with Czech language and coding applications. It is open‑source and can be fine‑tuned for specialized tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_07.1 GB 8.7 GB
Too big Get file →
BF1613.4 GB 15.0 GB
Too big Get file →
F3226.8 GB 28.4 GB
Too big Get file →

For 8 GB VRAM use Q8_0 (7.13 GB). For 12 GB VRAM use BF16 (13.41 GB). For 16 GB VRAM use F32 (26.82 GB). Memory estimates are approximate.

What GPU do you need for BUT FIT_csmpt7b?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.1 GB file, about 11.9 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (13.4 GB file, about 18.2 GB in use).
  • 32 GB VRAM: the best quant that fits is F32 (26.8 GB file, about 31.6 GB in use).

Which BUT FIT_csmpt7b quant should you choose?

BF16 (13.4 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is Q8_0 at 7.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturempt
Parameters6.7B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized byBUT-FIT
FamilyBut
RepositoryBUT-FIT/csmpt7b
Licenseapache-2.0
Downloads (HF)578
Last updated2025-05-21

Frequently asked questions about BUT FIT_csmpt7b

How much VRAM does BUT FIT_csmpt7b need?

About 18.2 GB at BF16 with an 8K context window. That is the 13.4 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 BUT FIT_csmpt7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BUT FIT_csmpt7b GGUF?

It depends on the quant: Q8_0 is 7.1 GB, BF16 is 13.4 GB, F32 is 26.8 GB.

What context length does BUT FIT_csmpt7b support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download BUT FIT_csmpt7b GGUF?

The files are on Hugging Face in the BUT-FIT/csmpt7b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does BUT FIT_csmpt7b 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.

Can I run Q8_0 on 8 GB VRAM?

Yes, Q8_0 is 7.13 GB and estimated to use 11.9 GB at 8k context, which fits 8 GB VRAM with some overhead.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license does the model use?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from BUT-FIT

All by BUT-FIT →

More But models

All But →

Other small models

All small models →