NU

Nu 17b

GGUFGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters16.8B
Context32K
Layers76
Architecturellama
Smallest quant6.4 GB
Quick answer

Nu 17b needs about 13.3 GB of memory at Q4_K_M (a 10.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 6.4 GB (Q2_K) to 18.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.2 GB.

Nu 17b – 16.8B llama model with roleplay capability

Nu 17b is a 16.8B parameter llama model trained on a 32768 token context. It is available in multiple GGUF quantizations and licensed under cc‑by‑nc‑4.0. The model supports roleplay tasks and is suitable for local deployment.

Good at

  • Roleplay scenarios
  • Text generation
  • Contextual dialogue

Limits

  • No vision support
  • cc‑by‑nc‑4.0 license restricts commercial use
  • Requires large VRAM for higher quants

Best for

  • Chatbot development
  • Creative writing
  • Interactive storytelling

Who it’s for. Developers and researchers needing a large llama model for local inference. The model is ideal for those who can run it on GPUs with sufficient VRAM and who comply with the cc‑by‑nc‑4.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.4 GB 9.5 GB
Too big Get file →
IQ3_XS7.1 GB 10.1 GB
Too big Get file →
Q3_K_S7.4 GB 10.5 GB
Too big Get file →
IQ3_S7.5 GB 10.5 GB
Too big Get file →
IQ3_M7.7 GB 10.8 GB
Too big Get file →
Q3_K_M8.3 GB 11.3 GB
Too big Get file →
Q3_K_L9.0 GB 12.1 GB
Too big Get file →
IQ4_XS9.3 GB 12.3 GB
Too big Get file →
Q4_K_S9.7 GB 12.8 GB
Too big Get file →
Q4_K_M10.3 GB 13.3 GB
Too big Get file →
Q5_K_S11.8 GB 14.8 GB
Too big Get file →
Q5_K_M12.1 GB 15.1 GB
Too big Get file →
Q6_K14.0 GB 17.0 GB
Too big Get file →
Q8_018.0 GB 21.1 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (6.4 GB file, ~9.5 GB memory). For 12 GB VRAM, Q4_K_S (9.73 GB file, ~12.8 GB memory) is a good balance. If you have 16 GB VRAM, Q5_K_M (12.07 GB file, ~15.1 GB memory) offers higher quality.

What GPU do you need for Nu 17b?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q3_K_M (8.3 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (12.1 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (18.0 GB file, about 21.1 GB in use).

Which Nu 17b quant should you choose?

Q4_K_M is the usual starting point for Nu 17b: it balances file size and quality well. Here it is a 10.3 GB file.

The Q8_0 file is 18.0 GB, about 1.8 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 6.4 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
Parameters16.8B
Layers76
Trained context32,768 tokens
KV cache (fp16)304 KB per token

Source

Quantized bymradermacher
Downloads (HF)2,103
Last updated2024-05-06

Frequently asked questions about Nu 17b

How much VRAM does Nu 17b need?

About 13.3 GB at Q4_K_M with an 8K context window. That is the 10.3 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 Nu 17b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nu 17b GGUF?

It depends on the quant: Q2_K is 6.4 GB, IQ3_XS is 7.1 GB, Q3_K_S is 7.4 GB, IQ3_S is 7.5 GB, IQ3_M is 7.7 GB, Q3_K_M is 8.3 GB and 8 more.

What context length does Nu 17b support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.6 GB at 8K and 10.2 GB at 32K.

Where can I download Nu 17b GGUF?

The files are on Hugging Face in the mradermacher/Nu-17b-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 Nu 17b use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Nu 17b on 8 GB VRAM?

Yes, the Q2_K quant uses 6.4 GB file and requires about 9.5 GB VRAM at 8k context.

Is Nu 17b suitable for commercial projects?

No, the cc‑by‑nc‑4.0 license prohibits commercial use without permission.

Does Nu 17b support image inputs?

No, the model has no vision capabilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other medium models

All medium models →