MI

Mistral Nemo 12B Instruct 2407

MistralGGUF by starble-devUpdated 2024-07-21
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant4.8 GB
Quick answer

Mistral Nemo 12B Instruct 2407 needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 4.8 GB (Q2_K) to 13.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Mistral Nemo 12B Instruct 2407 – 12.2B parameter LLM with 128k context

Mistral Nemo 12B Instruct 2407 is a 12.2B parameter transformer model trained with a 128k context window. It is an instruct fine‑tuned version of Mistral‑Nemo‑Base‑2407 and is released under the Apache 2.0 license.

Good at

  • Large context generation
  • Instruct following
  • Multilingual code understanding

Limits

  • No vision support
  • Requires CUDA for optimal performance
  • Large VRAM needed for higher quants

Best for

  • Chatbots needing long context
  • Code generation with context limits
  • Research prototyping of large LLMs

Who it’s for. Developers and researchers who need a 12B instruction‑tuned model with a 128k context window and are comfortable using llama.cpp or Hugging Face transformers. The model is suitable for applications that require extensive context handling and multilingual code support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 6.6 GB
Fits Get file →
Q3_K6.1 GB 7.9 GB
Tight Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q5_K_M8.7 GB 10.6 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 →
Q8_013.7 GB 15.5 GB
Too big Get file →

For 8 GB VRAM use Q4_K_S (file size 7.12 GB, ~9 GB memory at 8k context). For 12 GB VRAM use Q5_K_M (file size 8.73 GB, ~10.6 GB memory). For 16 GB VRAM use Q6_K (file size 10.06 GB, ~11.9 GB memory). Estimates are approximate.

What GPU do you need for Mistral Nemo 12B 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: the best quant that fits is Q3_K (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 (13.7 GB file, about 15.5 GB in use).

Which Mistral Nemo 12B Instruct 2407 quant should you choose?

Q4_K_M is the usual starting point for Mistral Nemo 12B Instruct 2407: it balances file size and quality well. Here it is a 7.5 GB file.

The Q8_0 file is 13.0 GB, about 1.7 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 Q2_K at 4.8 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 bystarble-dev
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,698
Last updated2024-07-21

Frequently asked questions about Mistral Nemo 12B Instruct 2407

How much VRAM does Mistral Nemo 12B Instruct 2407 need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 12B Instruct 2407 on an 8 GB GPU?

Yes, with Q3_K: 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 12B Instruct 2407 GGUF?

It depends on the quant: Q2_K is 4.8 GB, Q3_K is 6.1 GB, Q4_K_S is 7.1 GB, Q4_K_M is 7.5 GB, Q5_K_M is 8.7 GB, Q6_K is 10.1 GB and 2 more.

What context length does Mistral Nemo 12B 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 12B Instruct 2407 GGUF?

The files are on Hugging Face in the starble-dev/Mistral-Nemo-12B-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 12B 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.

Can I run Mistral Nemo 12B Instruct 2407 on 8 GB VRAM?

Yes, using the Q4_K_S quantization which requires about 9 GB of VRAM at 8k context.

Does the model support vision tasks?

No, the model does not have vision capabilities.

What license does the model use?

The model is released under the Apache 2.0 license.

Other GGUFs of Mistral-Nemo-Instruct-2407

Similar models

Browse all →

More from starble-dev

All by starble-dev →

More Mistral models

All Mistral →

Other medium models

All medium models →