NX

Nxcode-CQ-7B-orpo

NxcodeGGUF by LoneStrikerUpdated 2024-05-19
Download on Hugging Face
Parameters7.25B
Context64K
Layers32
Architectureqwen2
Smallest quant4.0 GB
Quick answer

Nxcode-CQ-7B-orpo needs about 5.8 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 4.0 GB (Q3_K_L) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

Nxcode-CQ-7B-orpo is a 7.25B-parameter Nxcode model in GGUF format, quantized by LoneStriker. Its trained context length is 64K tokens. The repository has 5 quant files, from 4.0 GB (Q3_K_L) to 7.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L4.0 GB 5.0 GB
Fits Get file →
Q4_K_M4.7 GB 5.8 GB
Fits Get file →
Q5_K_M5.4 GB 6.5 GB
Fits Get file →
Q6_K6.4 GB 7.4 GB
Tight Get file →
Q8_07.7 GB 8.7 GB
Too big Get file →

What GPU do you need for Nxcode-CQ-7B-orpo?

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 Q4_K_M (4.7 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.4 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 8.7 GB in use).

Which Nxcode-CQ-7B-orpo quant should you choose?

Q4_K_M is the usual starting point for Nxcode-CQ-7B-orpo: it balances file size and quality well. Here it is a 4.7 GB file.

The Q8_0 file is 7.7 GB, about 1.6 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_L at 4.0 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

Architectureqwen2
Parameters7.25B
Layers32
Trained context65,536 tokens
KV cache (fp16)64 KB per token

Source

Quantized byLoneStriker
FamilyNxcode
Licensemit
Downloads (HF)18
Last updated2024-05-19

Frequently asked questions about Nxcode-CQ-7B-orpo

How much VRAM does Nxcode-CQ-7B-orpo need?

About 5.8 GB at Q4_K_M with an 8K context window. That is the 4.7 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 Nxcode-CQ-7B-orpo on an 8 GB GPU?

Yes, with Q6_K: the 6.4 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nxcode-CQ-7B-orpo GGUF?

It depends on the quant: Q3_K_L is 4.0 GB, Q4_K_M is 4.7 GB, Q5_K_M is 5.4 GB, Q6_K is 6.4 GB, Q8_0 is 7.7 GB.

What context length does Nxcode-CQ-7B-orpo support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download Nxcode-CQ-7B-orpo GGUF?

The files are on Hugging Face in the LoneStriker/Nxcode-CQ-7B-orpo-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 Nxcode-CQ-7B-orpo use?

Hugging Face lists the license as mit. 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 LoneStriker

All by LoneStriker →

More Nxcode models

All Nxcode →

Other small models

All small models →