NE

Nemomix v4.0 12B

NemomixGGUF by Reiterate3680Updated 2024-08-05
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant4.4 GB
Quick answer

Nemomix v4.0 12B needs about 9.8 GB of memory at Q4_K_M (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 10 quants, from 4.4 GB (IQ2_M) to 10.4 GB (Q6_K_L). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Nemomix v4.0 12B is a 12.2B-parameter Nemomix model in GGUF format, quantized by Reiterate3680. Its trained context length is 1000K tokens. The repository has 10 quant files, from 4.4 GB (IQ2_M) to 10.4 GB (Q6_K_L).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M4.4 GB 6.3 GB
Fits Get file →
Q2_K_S4.5 GB 6.3 GB
Fits Get file →
IQ3_M5.7 GB 7.6 GB
Tight Get file →
Q3_K_L6.6 GB 8.4 GB
Too big Get file →
IQ4_XS6.7 GB 8.6 GB
Too big Get file →
Q4_K_M8.0 GB 9.8 GB
Too big Get file →
Q4_K_L8.0 GB 9.8 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 →
Q6_K_L10.4 GB 12.2 GB
Too big Get file →

What GPU do you need for Nemomix v4.0 12B?

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 IQ3_M (5.7 GB file, about 7.6 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 Q6_K_L (10.4 GB file, about 12.2 GB in use).

Which Nemomix v4.0 12B quant should you choose?

Q4_K_M is the usual starting point for Nemomix v4.0 12B: it balances file size and quality well. Here it is a 8.0 GB file.

If memory is tight, the smallest file is IQ2_M at 4.4 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 byReiterate3680
FamilyNemomix
Licenseother
Downloads (HF)230
Last updated2024-08-05

Frequently asked questions about Nemomix v4.0 12B

How much VRAM does Nemomix v4.0 12B need?

About 9.8 GB at Q4_K_M with an 8K context window. That is the 8.0 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 Nemomix v4.0 12B on an 8 GB GPU?

Yes, with IQ3_M: the 5.7 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nemomix v4.0 12B GGUF?

It depends on the quant: IQ2_M is 4.4 GB, Q2_K_S is 4.5 GB, IQ3_M is 5.7 GB, Q3_K_L is 6.6 GB, IQ4_XS is 6.7 GB, Q4_K_M is 8.0 GB and 4 more.

What context length does Nemomix v4.0 12B 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 Nemomix v4.0 12B GGUF?

The files are on Hugging Face in the Reiterate3680/Nemomix-v4.0-12B-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 Nemomix v4.0 12B 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.

Other GGUFs of Nemomix-v4.0-12B

Similar models

Browse all →

More from Reiterate3680

All by Reiterate3680 →

More Nemomix models

All Nemomix →

Other medium models

All medium models →