MI

cloudyu mistral 28B instruct v0.1

MistralGGUF by RichardErkhovUpdated 2024-10-31
Download on Hugging Face
Parameters28.2B
Context32K
Layers—
Architecturellama
Smallest quant3.3 GB
Quick answer

cloudyu mistral 28B instruct v0.1 needs about 13.2 GB of memory at Q4_K_M (a 11.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 19 quants, from 3.3 GB (Q6_K) to 21.1 GB (Q5_1).

cloudyu mistral 28B instruct v0.1 is a 28.2B-parameter Mistral model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 19 quant files, from 3.3 GB (Q6_K) to 21.1 GB (Q5_1).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K3.3 GB 4.2 GB
Fits Get file →
Q4_06.7 GB 8.0 GB
Tight Get file →
Q2_K10.4 GB 12.2 GB
Too big Get file →
Q4_K_M11.3 GB 13.2 GB
Too big Get file →
Q3_K_S12.2 GB 14.1 GB
Too big Get file →
Q3_K13.6 GB 15.7 GB
Too big Get file →
Q3_K_M13.6 GB 15.7 GB
Too big Get file →
Q3_K_L14.8 GB 17.1 GB
Too big Get file →
IQ4_XS15.2 GB 17.6 GB
Too big Get file →
Q4_K_S16.0 GB 18.4 GB
Too big Get file →
IQ4_NL16.1 GB 18.5 GB
Too big Get file →
Q8_016.8 GB 19.3 GB
Too big Get file →
Q4_K16.9 GB 19.5 GB
Too big Get file →
Q4_117.6 GB 20.3 GB
Too big Get file →
Q5_019.4 GB 22.2 GB
Too big Get file →
Q5_K_S19.4 GB 22.2 GB
Too big Get file →
Q5_K19.9 GB 22.8 GB
Too big Get file →
Q5_K_M19.9 GB 22.8 GB
Too big Get file →
Q5_121.1 GB 24.2 GB
Too big Get file →

What GPU do you need for cloudyu mistral 28B instruct v0.1?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q6_K (3.3 GB file, about 4.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_0 (6.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_0 (6.7 GB file, about 8.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K (13.6 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K (19.9 GB file, about 22.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_1 (21.1 GB file, about 24.2 GB in use).

Which cloudyu mistral 28B instruct v0.1 quant should you choose?

Q4_K_M is the usual starting point for cloudyu mistral 28B instruct v0.1: it balances file size and quality well. Here it is a 11.3 GB file.

The Q8_0 file is 16.8 GB, about 1.5 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.

If memory is tight, the smallest file is Q6_K at 3.3 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters28.2B
Trained context32,768 tokens

Source

Quantized byRichardErkhov
FamilyMistral
Downloads (HF)159
Last updated2024-10-31

Frequently asked questions about cloudyu mistral 28B instruct v0.1

How much VRAM does cloudyu mistral 28B instruct v0.1 need?

About 13.2 GB at Q4_K_M with an 8K context window. That is the 11.3 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 cloudyu mistral 28B instruct v0.1 on an 8 GB GPU?

Yes, with Q4_0: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of cloudyu mistral 28B instruct v0.1 GGUF?

It depends on the quant: Q6_K is 3.3 GB, Q4_0 is 6.7 GB, Q2_K is 10.4 GB, Q4_K_M is 11.3 GB, Q3_K_S is 12.2 GB, Q3_K is 13.6 GB and 13 more.

What context length does cloudyu mistral 28B instruct v0.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K).

Where can I download cloudyu mistral 28B instruct v0.1 GGUF?

The files are on Hugging Face in the RichardErkhov/cloudyu_-_mistral_28B_instruct_v0.1-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 RichardErkhov

All by RichardErkhov →

More Mistral models

All Mistral →

Other medium models

All medium models →