LL

Upstage Llama1 65B Instruct

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters65B
Context2K
Layers80
Architecturellama
Smallest quant27.0 GB
Quick answer

Upstage Llama1 65B Instruct needs about 61.3 GB of memory at Q4_K_M (a 39.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 10 quants, from 27.0 GB (Q2_K) to 46.2 GB (Q5_K_M).

Upstage Llama1 65B Instruct – large‑scale instruction‑tuned LLaMA

Upstage Llama1 65B Instruct is a 65‑billion‑parameter LLaMA model fine‑tuned on an Orca‑style dataset. It supports up to 2048 context tokens and is available in multiple GGUF quantisations. The model is released under a non‑commercial bespoke license.

Good at

  • Instruction following
  • Long‑form generation
  • Multi‑turn dialogue

Limits

  • Requires large VRAM for full precision
  • No vision or multimodal support
  • Non‑commercial license restrictions

Best for

  • Enterprise chatbots
  • Research prototyping
  • Custom fine‑tuning

Who it’s for. Developers and researchers who need a powerful instruction‑tuned LLaMA model for local inference. The model is suitable for those with access to the required license and sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K27.0 GB 32.9 GB
Too big Get file →
Q3_K_S28.2 GB 34.0 GB
Too big Get file →
Q3_K_M31.6 GB 37.4 GB
Too big Get file →
Q3_K_L34.6 GB 40.5 GB
Too big Get file →
Q4_036.8 GB 42.7 GB
Too big Get file →
Q4_K_S36.9 GB 42.8 GB
Too big Get file →
Q4_K_M39.3 GB 45.2 GB
Too big Get file →
Q5_044.9 GB 50.8 GB
Too big Get file →
Q5_K_S44.9 GB 50.8 GB
Too big Get file →
Q5_K_M46.2 GB 52.1 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K or Q4_K_S (≈58.8‑58.9 GB memory at 8k context). For 12‑GB VRAM, Q5_K_S or Q5_K_M (≈66.9‑68.2 GB). For 16‑GB VRAM, Q4_K_M (≈61.3 GB). Memory estimates are approximate.

What GPU do you need for Upstage Llama1 65B Instruct?

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: no quant fits at an 8K context.

Which Upstage Llama1 65B Instruct quant should you choose?

Q4_K_M is the usual starting point for Upstage Llama1 65B Instruct: it balances file size and quality well. Here it is a 39.3 GB file.

If memory is tight, the smallest file is Q2_K at 27.0 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
Parameters65B
Layers80
Trained context2,048 tokens
KV cache (fp16)2560 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licenseother
Downloads (HF)2,645
Last updated2023-09-27

Frequently asked questions about Upstage Llama1 65B Instruct

How much VRAM does Upstage Llama1 65B Instruct need?

About 61.3 GB at Q4_K_M with an 8K context window. That is the 39.3 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 Upstage Llama1 65B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 49.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Upstage Llama1 65B Instruct GGUF?

It depends on the quant: Q2_K is 27.0 GB, Q3_K_S is 28.2 GB, Q3_K_M is 31.6 GB, Q3_K_L is 34.6 GB, Q4_0 is 36.8 GB, Q4_K_S is 36.9 GB and 4 more.

What context length does Upstage Llama1 65B Instruct support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 21.5 GB at 8K and 5.4 GB at 2K.

Where can I download Upstage Llama1 65B Instruct GGUF?

The files are on Hugging Face in the TheBloke/Upstage-Llama1-65B-Instruct-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 Upstage Llama1 65B Instruct 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?

Only the Q4_K or Q4_K_S quantisations can fit, using about 58.8‑58.9 GB of VRAM at 8k context, which exceeds 8 GB. Smaller VRAM requires lower‑bit quantisations not listed.

Does this model support vision tasks?

No, the model has no vision or multimodal capabilities.

What license applies to this model?

It is under a non‑commercial bespoke license governed by the Meta license, and requires permission from Upstage.

Other GGUFs of llama-65b-instruct

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other large models

All large models →