MI

Mistral Nemo Instruct 2407

MistralGGUF by mmngaUpdated 2024-07-22
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant3.0 GB
Quick answer

Mistral Nemo Instruct 2407 needs about 7.4 GB of memory at IQ3_S (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 3.0 GB (IQ1_S) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Mistral Nemo Instruct 2407 is a 12.2B-parameter Mistral model in GGUF format, quantized by mmnga. Its trained context length is 1000K tokens. The repository has 21 quant files, from 3.0 GB (IQ1_S) to 13.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.0 GB 4.8 GB
Fits Get file →
IQ1_M3.2 GB 5.1 GB
Fits Get file →
IQ2_XXS3.6 GB 5.4 GB
Fits Get file →
IQ2_XS3.9 GB 5.8 GB
Fits Get file →
IQ2_S4.1 GB 6.0 GB
Fits Get file →
IQ2_M4.4 GB 6.3 GB
Fits Get file →
Q2_K4.8 GB 6.6 GB
Fits Get file →
IQ3_XXS4.9 GB 6.8 GB
Fits Get file →
IQ3_XS5.3 GB 7.1 GB
Fits Get file →
Q3_K_S5.5 GB 7.4 GB
Tight Get file →
IQ3_S5.6 GB 7.4 GB
Tight Get file →
IQ3_M5.7 GB 7.6 GB
Tight Get file →
Q3_K_M6.1 GB 7.9 GB
Tight Get file →
Q3_K_L6.6 GB 8.4 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
IQ4_NL7.1 GB 8.9 GB
Too big Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q5_08.5 GB 10.4 GB
Too big Get file →
Q5_K_S8.5 GB 10.4 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →

What GPU do you need for Mistral Nemo 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: the best quant that fits is IQ2_S (4.1 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).

Which Mistral Nemo Instruct 2407 quant should you choose?

IQ3_S (5.6 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 3.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymmnga
FamilyMistral
Licenseapache-2.0
Downloads (HF)109
Last updated2024-07-22

Frequently asked questions about Mistral Nemo Instruct 2407

How much VRAM does Mistral Nemo Instruct 2407 need?

About 7.4 GB at IQ3_S with an 8K context window. That is the 5.6 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 Nemo Instruct 2407 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.1 GB, IQ2_M is 4.4 GB and 15 more.

What context length does Mistral Nemo Instruct 2407 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Mistral Nemo Instruct 2407 GGUF?

The files are on Hugging Face in the mmnga/Mistral-Nemo-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 Nemo Instruct 2407 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 mmnga

All by mmnga →

More Mistral models

All Mistral →

Other medium models

All medium models →