AL

totally-not-an-llm_alpacacielo2-7b-8k

AlpacacieloGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters6.74B
Context8K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

totally-not-an-llm_alpacacielo2-7b-8k 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).

AlpacaCielo2‑7B‑8K – a 6.74B llama‑2 model for creative chat

AlpacaCielo2‑7B‑8K is a 6.74B llama‑2 based model with an 8192 token context. It merges Nous‑Hermes, Guanaco, and LimaRP for improved role‑playing and storytelling. The model is mostly uncensored but retains some Guanaco alignment.

Good at

  • Creative storytelling
  • Role‑play dialogues
  • Chatbot assistance

Limits

  • No vision support
  • License: llama2
  • Requires 8k context for full capability

Best for

  • Writing short stories
  • Character dialogue generation
  • Chatbot prototyping

Who it’s for. Developers and hobbyists looking for a lightweight creative LLM. It is suitable for local inference with llama.cpp or compatible GUIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 7.6 GB
Tight Get file →
Q3_K_S2.9 GB 7.7 GB
Tight Get file →
Q3_K_M3.3 GB 8.1 GB
Too big Get file →
Q3_K_L3.6 GB 8.4 GB
Too big Get file →
Q4_03.8 GB 8.6 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q5_04.7 GB 9.4 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →

For 8 GB VRAM use Q2_K (2.83 GB, 7.6 GB memory) or Q3_K_S (2.95 GB, 7.7 GB). For 12 GB VRAM Q4_K_M (4.08 GB, 8.9 GB) or Q5_K_M (4.78 GB, 9.6 GB) are good choices. Higher quants like Q6_K (5.53 GB, 10.3 GB) need more memory.

What GPU do you need for totally-not-an-llm_alpacacielo2-7b-8k?

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 totally-not-an-llm_alpacacielo2-7b-8k quant should you choose?

Q4_K_M is the usual starting point for totally-not-an-llm_alpacacielo2-7b-8k: 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 context8,192 tokens
KV cache (fp16)512 KB per token

Source

Quantized byTheBloke
Licensellama2
Downloads (HF)1,469
Last updated2023-09-27

Frequently asked questions about totally-not-an-llm_alpacacielo2-7b-8k

How much VRAM does totally-not-an-llm_alpacacielo2-7b-8k 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 totally-not-an-llm_alpacacielo2-7b-8k 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 totally-not-an-llm_alpacacielo2-7b-8k 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 totally-not-an-llm_alpacacielo2-7b-8k support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 4.3 GB at 8K and 4.3 GB at 8K.

Where can I download totally-not-an-llm_alpacacielo2-7b-8k GGUF?

The files are on Hugging Face in the TheBloke/AlpacaCielo2-7B-8K-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 totally-not-an-llm_alpacacielo2-7b-8k use?

Hugging Face lists the license as llama2. 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 AlpacaCielo2‑7B‑8K on 8 GB VRAM?

Yes, the Q2_K quant uses 2.83 GB file size and needs about 7.6 GB VRAM at 8k context.

Does the model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The model is licensed under llama2.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Alpacacielo models

All Alpacacielo →

Other small models

All small models →