MI

Vikhr Nemo 12B Instruct R 21 09 24

MistralGGUF by Alex01837178373Updated 2024-09-21
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant6.1 GB
Quick answer

Vikhr Nemo 12B Instruct R 21 09 24 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 6 quants, from 6.1 GB (Q3_K_M) to 24.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Vikhr Nemo 12B Instruct R 21 09 24 is a 12.2B-parameter Mistral model in GGUF format, quantized by Alex01837178373. Its trained context length is 1000K tokens. The repository has 6 quant files, from 6.1 GB (Q3_K_M) to 24.5 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M6.1 GB 7.9 GB
Tight 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 →
BF1624.5 GB 26.3 GB
Too big Get file →

What GPU do you need for Vikhr Nemo 12B Instruct R 21 09 24?

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_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).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (24.5 GB file, about 26.3 GB in use).

Which Vikhr Nemo 12B Instruct R 21 09 24 quant should you choose?

Q4_K_M is the usual starting point for Vikhr Nemo 12B Instruct R 21 09 24: 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 Q3_K_M at 6.1 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
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized byAlex01837178373
FamilyMistral
Licenseapache-2.0
Downloads (HF)175
Last updated2024-09-21

Frequently asked questions about Vikhr Nemo 12B Instruct R 21 09 24

How much VRAM does Vikhr Nemo 12B Instruct R 21 09 24 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 Vikhr Nemo 12B Instruct R 21 09 24 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 Vikhr Nemo 12B Instruct R 21 09 24 GGUF?

It depends on the quant: Q3_K_M is 6.1 GB, Q4_K_M is 7.5 GB, Q5_K_M is 8.7 GB, Q6_K is 10.1 GB, Q8_0 is 13.0 GB, BF16 is 24.5 GB.

What context length does Vikhr Nemo 12B Instruct R 21 09 24 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 Vikhr Nemo 12B Instruct R 21 09 24 GGUF?

The files are on Hugging Face in the Alex01837178373/Vikhr-Nemo-12B-Instruct-R-21-09-24-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 Vikhr Nemo 12B Instruct R 21 09 24 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.

Other GGUFs of Mistral-Nemo-Instruct-2407

Similar models

Browse all →

More from Alex01837178373

All by Alex01837178373 →

More Mistral models

All Mistral →

Other medium models

All medium models →