MI

cloudyu mistral 28B instruct v0.2

MistralGGUF by RichardErkhovUpdated 2024-10-31
Download on Hugging Face
Parameters28B
Context32K
Layers128
Architecturellama
Smallest quant4.4 GB
Quick answer

cloudyu mistral 28B instruct v0.2 needs about 21.7 GB of memory at Q4_K_M (a 16.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 19 quants, from 4.4 GB (IQ4_NL) to 23.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

cloudyu mistral 28B instruct v0.2 is a 28B-parameter Mistral model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 19 quant files, from 4.4 GB (IQ4_NL) to 23.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL4.4 GB 9.2 GB
Too big Get file →
Q4_04.9 GB 9.7 GB
Too big Get file →
Q8_06.7 GB 11.5 GB
Too big Get file →
Q2_K10.4 GB 15.2 GB
Too big Get file →
Q3_K_S12.2 GB 17.0 GB
Too big Get file →
Q3_K13.6 GB 18.4 GB
Too big Get file →
Q3_K_M13.6 GB 18.4 GB
Too big Get file →
Q3_K_L14.8 GB 19.6 GB
Too big Get file →
IQ4_XS15.2 GB 20.0 GB
Too big Get file →
Q4_K_S16.0 GB 20.8 GB
Too big Get file →
Q4_K16.9 GB 21.7 GB
Too big Get file →
Q4_K_M16.9 GB 21.7 GB
Too big Get file →
Q4_117.6 GB 22.4 GB
Too big Get file →
Q5_019.4 GB 24.2 GB
Too big Get file →
Q5_K_S19.4 GB 24.2 GB
Too big Get file →
Q5_K19.9 GB 24.7 GB
Too big Get file →
Q5_K_M19.9 GB 24.7 GB
Too big Get file →
Q5_121.1 GB 25.9 GB
Too big Get file →
Q6_K23.1 GB 27.9 GB
Too big Get file →

What GPU do you need for cloudyu mistral 28B instruct v0.2?

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 (6.7 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (10.4 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (17.6 GB file, about 22.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (23.1 GB file, about 27.9 GB in use).

Which cloudyu mistral 28B instruct v0.2 quant should you choose?

Q4_K_M is the usual starting point for cloudyu mistral 28B instruct v0.2: it balances file size and quality well. Here it is a 16.9 GB file.

The Q8_0 file is 6.7 GB, about 0.4 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 IQ4_NL at 4.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters28B
Layers128
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized byRichardErkhov
FamilyMistral
Licensecc-by-4.0
Downloads (HF)118
Last updated2024-10-31

Frequently asked questions about cloudyu mistral 28B instruct v0.2

How much VRAM does cloudyu mistral 28B instruct v0.2 need?

About 21.7 GB at Q4_K_M with an 8K context window. That is the 16.9 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 v0.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of cloudyu mistral 28B instruct v0.2 GGUF?

It depends on the quant: IQ4_NL is 4.4 GB, Q4_0 is 4.9 GB, Q8_0 is 6.7 GB, Q2_K is 10.4 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 v0.2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download cloudyu mistral 28B instruct v0.2 GGUF?

The files are on Hugging Face in the RichardErkhov/cloudyu_-_mistral_28B_instruct_v0.2-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 cloudyu mistral 28B instruct v0.2 use?

Hugging Face lists the license as cc-by-4.0. 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 RichardErkhov

All by RichardErkhov →

More Mistral models

All Mistral →

Other medium models

All medium models →