MI

Mistral Large Instruct 2407

MistralGGUF by RichardErkhovUpdated 2024-08-17
Download on Hugging Face
Parameters120B
Context32K
Layers88
Architecturellama
Smallest quant6.5 GB
Quick answer

Mistral Large Instruct 2407 needs about 76.7 GB of memory at Q4_K_M (a 73.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 22 quants, from 6.5 GB (IQ3_XS) to 130.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

Mistral Large Instruct 2407 is a 120B-parameter Mistral model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 6.5 GB (IQ3_XS) to 130.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XS6.5 GB 10.0 GB
Too big Get file →
Q2_K45.2 GB (2 parts) 48.6 GB
Too big Get file →
Q3_K_S52.8 GB (2 parts) 56.3 GB
Too big Get file →
IQ3_S53.0 GB (2 parts) 56.4 GB
Too big Get file →
IQ3_M55.3 GB (2 parts) 58.7 GB
Too big Get file →
Q3_K59.1 GB (2 parts) 62.6 GB
Too big Get file →
Q3_K_M59.1 GB (2 parts) 62.6 GB
Too big Get file →
Q3_K_L64.6 GB (2 parts) 68.0 GB
Too big Get file →
IQ4_XS66.0 GB (2 parts) 69.5 GB
Too big Get file →
Q4_069.1 GB (2 parts) 72.5 GB
Too big Get file →
Q4_K_S69.6 GB (2 parts) 73.0 GB
Too big Get file →
IQ4_NL69.7 GB (2 parts) 73.2 GB
Too big Get file →
Q4_K73.2 GB (2 parts) 76.7 GB
Too big Get file →
Q4_K_M73.2 GB (2 parts) 76.7 GB
Too big Get file →
Q4_176.7 GB (2 parts) 80.2 GB
Too big Get file →
Q5_084.4 GB (3 parts) 87.8 GB
Too big Get file →
Q5_K_S84.4 GB (3 parts) 87.8 GB
Too big Get file →
Q5_K86.5 GB (3 parts) 89.9 GB
Too big Get file →
Q5_K_M86.5 GB (3 parts) 89.9 GB
Too big Get file →
Q5_192.0 GB (3 parts) 95.4 GB
Too big Get file →
Q6_K100.6 GB (3 parts) 104.0 GB
Too big Get file →
Q8_0130.3 GB (4 parts) 133.7 GB
Too big Get file →

What GPU do you need for Mistral Large Instruct 2407?

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 IQ3_XS (6.5 GB file, about 10.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (6.5 GB file, about 10.0 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_XS (6.5 GB file, about 10.0 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XS (6.5 GB file, about 10.0 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_XS (6.5 GB file, about 10.0 GB in use).

Which Mistral Large Instruct 2407 quant should you choose?

Q4_K_M is the usual starting point for Mistral Large Instruct 2407: it balances file size and quality well. Here it is a 73.2 GB file.

The Q8_0 file is 130.3 GB, about 1.8 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 IQ3_XS at 6.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters120B
Layers88
Trained context32,768 tokens
KV cache (fp16)352 KB per token

Source

Quantized byRichardErkhov
FamilyMistral
Licenseother
Downloads (HF)132
Last updated2024-08-17

Frequently asked questions about Mistral Large Instruct 2407

How much VRAM does Mistral Large Instruct 2407 need?

About 76.7 GB at Q4_K_M with an 8K context window. That is the 73.2 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 Mistral Large Instruct 2407 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Large Instruct 2407 GGUF?

It depends on the quant: IQ3_XS is 6.5 GB, Q2_K is 45.2 GB, Q3_K_S is 52.8 GB, IQ3_S is 53.0 GB, IQ3_M is 55.3 GB, Q3_K is 59.1 GB and 16 more.

What context length does Mistral Large Instruct 2407 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.

Where can I download Mistral Large Instruct 2407 GGUF?

The files are on Hugging Face in the RichardErkhov/SillyTilly_-_Mistral-Large-Instruct-2407-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 Mistral Large Instruct 2407 use?

Hugging Face lists the license as other. 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 large models

All large models →