LL

nkpz_llama2-22b-daydreamer-v3

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters21.8B
Context4K
Layers40
Architecturellama
Smallest quant9.1 GB
Quick answer

nkpz_llama2-22b-daydreamer-v3 needs about 22.4 GB of memory at Q4_K_M (a 13.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 9.1 GB (Q2_K) to 23.2 GB (Q8_0).

Llama2 22B Daydreamer v3 in GGUF format

nkpz_llama2-22b-daydreamer-v3 is a 21.8B parameter Llama model fine‑tuned for English instruction and roleplay. It supports 4098 token context and is available in multiple GGUF quantisations. The model is released under an other license.

Good at

  • English instruction following
  • Roleplay and speech style imitation
  • Dry, accurate factual answers

Limits

  • No vision support
  • License is other, not standard
  • Requires large VRAM for higher quants

Best for

  • Chatbot applications
  • Story generation
  • Educational tutoring

Who it’s for. Developers and researchers who need a large Llama model for local inference. The model is suitable for users with GPU hardware capable of handling 8‑k context and the chosen quantisation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K9.1 GB 13.9 GB
Too big Get file →
Q3_K_S9.5 GB 14.3 GB
Too big Get file →
Q3_K_M10.6 GB 15.5 GB
Too big Get file →
Q3_K_L11.6 GB 16.5 GB
Too big Get file →
Q4_012.3 GB 17.2 GB
Too big Get file →
Q4_K_S12.4 GB 17.3 GB
Too big Get file →
Q4_K_M13.2 GB 18.0 GB
Too big Get file →
Q5_015.0 GB 19.9 GB
Too big Get file →
Q5_K_S15.0 GB 19.9 GB
Too big Get file →
Q5_K_M15.5 GB 20.3 GB
Too big Get file →
Q6_K17.9 GB 22.8 GB
Too big Get file →
Q8_023.2 GB 28.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K or Q4_0 (est. 21.6 GB memory at 8k context). For 12 GB VRAM, Q5_K_M or Q5_0 (est. 24.3 GB). For 16 GB VRAM, Q6_K (est. 27.1 GB). Higher quants need more VRAM.

What GPU do you need for nkpz_llama2-22b-daydreamer-v3?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (13.2 GB file, about 22.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (17.9 GB file, about 27.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (23.2 GB file, about 32.4 GB in use).

Which nkpz_llama2-22b-daydreamer-v3 quant should you choose?

Q4_K_M is the usual starting point for nkpz_llama2-22b-daydreamer-v3: it balances file size and quality well. Here it is a 13.2 GB file.

The Q8_0 file is 23.2 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 9.1 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
Parameters21.8B
Layers40
Trained context4,098 tokens
KV cache (fp16)1040 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licenseother
Downloads (HF)2,074
Last updated2023-09-27

Frequently asked questions about nkpz_llama2-22b-daydreamer-v3

How much VRAM does nkpz_llama2-22b-daydreamer-v3 need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 13.2 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 nkpz_llama2-22b-daydreamer-v3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of nkpz_llama2-22b-daydreamer-v3 GGUF?

It depends on the quant: Q2_K is 9.1 GB, Q3_K_S is 9.5 GB, Q3_K_M is 10.6 GB, Q3_K_L is 11.6 GB, Q4_0 is 12.3 GB, Q4_K_S is 12.4 GB and 6 more.

What context length does nkpz_llama2-22b-daydreamer-v3 support?

The GGUF header lists a trained context length of 4,098 tokens (4K). The KV cache grows with the context you use: about 8.7 GB at 8K and 4.4 GB at 4K.

Where can I download nkpz_llama2-22b-daydreamer-v3 GGUF?

The files are on Hugging Face in the TheBloke/Llama2-22B-Daydreamer-v3-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 nkpz_llama2-22b-daydreamer-v3 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.

Can I run this model on 8 GB VRAM?

Use Q4_K or Q4_0 quantisation; estimated memory is 21.6 GB at 8k context, so 8 GB is insufficient.

Does this model support vision tasks?

No, the model has no vision capability.

What license applies to this model?

The model is released under an other license, not a standard open‑source license.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other medium models

All medium models →