KU

Kuchiki 1.1 L2 7B

KuchikiGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

Kuchiki 1.1 L2 7B needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 2.8 GB (Q2_K) to 7.2 GB (Q8_0).

Kuchiki 1.1 L2 7B – a merged Llama‑based model

Kuchiki 1.1 L2 7B merges Nous Hermes Llama2 7b, Airoboros L2 7B GPT4 2.0, and LimaRP Llama2 v2 7B LoRA. It is available in GGUF format and supports llama.cpp and other GGUF clients. The model was trained with a context length of 4096 tokens.

Good at

  • Merged instruction formats (Alpaca 2, Alpaca LimaRP)
  • Llama‑based conversational tasks
  • LoRA‑enhanced responses

Limits

  • No vision support
  • License is other, not open source
  • Context limited to 4096 tokens

Best for

  • Chatbot prototypes
  • Story generation with LoRA styles
  • Local inference on moderate GPUs

Who it’s for. Developers and researchers who need a merged Llama‑based model for local inference. It is suitable for those who use llama.cpp or compatible GUIs and require a model with multiple instruction formats.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 5.5 GB
Fits Get file →
Q3_K_S2.9 GB 5.6 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.2 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_K_S3.9 GB 6.5 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q5_04.7 GB 7.3 GB
Tight Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →
Q8_07.2 GB 9.8 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (est. 8.9 GB memory). For 12 GB VRAM use Q8_0 (est. 12 GB memory). For 6 GB VRAM use Q3_K_S (est. 7.7 GB memory) or Q2_K (est. 7.6 GB memory).

What GPU do you need for Kuchiki 1.1 L2 7B?

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_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which Kuchiki 1.1 L2 7B quant should you choose?

Q4_K_M is the usual starting point for Kuchiki 1.1 L2 7B: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.8 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
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byTheBloke
FamilyKuchiki
Licenseother
Downloads (HF)2,119
Last updated2023-09-27

Frequently asked questions about Kuchiki 1.1 L2 7B

How much VRAM does Kuchiki 1.1 L2 7B need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Kuchiki 1.1 L2 7B on an 8 GB GPU?

Yes, with Q3_K_S: the 2.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kuchiki 1.1 L2 7B GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.3 GB, Q3_K_L is 3.6 GB, Q4_0 is 3.8 GB, Q4_K_S is 3.9 GB and 6 more.

What context length does Kuchiki 1.1 L2 7B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Kuchiki 1.1 L2 7B GGUF?

The files are on Hugging Face in the TheBloke/Kuchiki-1.1-L2-7B-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 Kuchiki 1.1 L2 7B 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 Kuchiki 1.1 L2 7B on 8 GB VRAM?

Yes, using Q4_K_M or Q4_K_S will fit within 8 GB VRAM, though memory usage is approximate.

Does this model support vision?

No, the model has no vision capabilities.

What context length does it support?

It supports up to 4096 tokens.

Other GGUFs of kuchiki-1.1-l2-7b

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Kuchiki models

All Kuchiki →

Other small models

All small models →