LO

LongAlpaca 70B

LongalpacaGGUF by TheBlokeUpdated 2023-10-15
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant29.3 GB
Quick answer

LongAlpaca 70B needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 29.3 GB (Q2_K) to 48.8 GB (Q5_K_M).

LongAlpaca 70B – a 70‑billion‑parameter LLM with extended context

LongAlpaca 70B is a 69‑billion‑parameter model fine‑tuned on the LongAlpaca‑12k instruction‑following dataset. It supports a 4096‑token context window and is released under the llama2 license. The model is available in multiple GGUF quantisations for efficient inference.

Good at

  • Long‑context instruction following
  • Large‑scale text generation
  • Fine‑tuned for Alpaca style prompts

Limits

  • No vision support
  • Requires GPU for efficient inference
  • Large VRAM needed for higher quantisations

Best for

  • Chatbots needing long context
  • Research on instruction‑following models
  • Generating long documents

Who it’s for. Developers and researchers who need a large‑parameter LLM with extended context for text generation tasks. The model is suitable for local deployment via llama.cpp or compatible GUIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.3 GB 31.1 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_M33.2 GB 35.0 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
Q4_038.9 GB 40.7 GB
Too big Get file →
Q4_K_S39.1 GB 40.9 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_047.5 GB 49.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S or Q4_K_M (≈42 GB memory at 8k context). For 16 GB VRAM, Q5_K_S or Q5_K_M are suitable (≈51 GB memory). For 32 GB VRAM, Q4_0 or Q5_0 provide a balance between size and performance.

What GPU do you need for LongAlpaca 70B?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which LongAlpaca 70B quant should you choose?

Q4_K_M is the usual starting point for LongAlpaca 70B: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 29.3 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
Licensellama2
Downloads (HF)2,064
Last updated2023-10-15

Frequently asked questions about LongAlpaca 70B

How much VRAM does LongAlpaca 70B need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 LongAlpaca 70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LongAlpaca 70B GGUF?

It depends on the quant: Q2_K is 29.3 GB, Q3_K_S is 29.9 GB, Q3_K_M is 33.2 GB, Q3_K_L is 36.1 GB, Q4_0 is 38.9 GB, Q4_K_S is 39.1 GB and 4 more.

What context length does LongAlpaca 70B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download LongAlpaca 70B GGUF?

The files are on Hugging Face in the TheBloke/LongAlpaca-70B-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 LongAlpaca 70B 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 LongAlpaca 70B on 8 GB VRAM?

Only the lowest quantisations such as Q2_K or Q3_K_S can fit, but they still require more than 8 GB VRAM at 8k context. 8 GB VRAM is insufficient for any 70B quantisation.

Does LongAlpaca 70B support vision tasks?

No. The model has no vision capabilities and is text‑only.

What license applies to LongAlpaca 70B?

The model is released under the llama2 license, which requires acceptance of Meta’s license terms.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Longalpaca models

All Longalpaca →

Other large models

All large models →