LL

ORCA LLaMA 70B QLoRA

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant29.3 GB
Quick answer

ORCA LLaMA 70B QLoRA 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).

ORCA LLaMA 70B QLoRA – a fine‑tuned 70B Llama model in GGUF format

ORCA LLaMA 70B QLoRA is a 69 billion‑parameter Llama model fine‑tuned on the ORCA dataset. It is available in GGUF format and supports 4096‑token context. The model is released under the llama2 license.

Good at

  • Fine‑tuned on ORCA data
  • Large 70B parameter size
  • Supports 4096‑token context

Limits

  • Requires large VRAM for higher quants
  • No vision capabilities
  • License restricts commercial use

Best for

  • Research on large‑scale LLMs
  • Fine‑tuning experiments
  • Benchmarking quantisation effects

Who it’s for. Developers and researchers who need a large Llama model with ORCA fine‑tuning. The model is suitable for local inference on systems with sufficient GPU memory and for those who comply with the llama2 license.

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 (file size 39.07 GB, estimated 42.3 GB memory). For 12 GB VRAM, Q4_K_M (41.42 GB, 44.6 GB memory) is suitable. For 16 GB VRAM, Q5_K_S (47.46 GB, 50.6 GB memory) can be used. Memory estimates are approximate.

What GPU do you need for ORCA LLaMA 70B QLoRA?

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 ORCA LLaMA 70B QLoRA quant should you choose?

Q4_K_M is the usual starting point for ORCA LLaMA 70B QLoRA: 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
FamilyLlama
Licensellama2
Downloads (HF)1,577
Last updated2023-09-27

Frequently asked questions about ORCA LLaMA 70B QLoRA

How much VRAM does ORCA LLaMA 70B QLoRA 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 ORCA LLaMA 70B QLoRA 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 ORCA LLaMA 70B QLoRA 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 ORCA LLaMA 70B QLoRA 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 ORCA LLaMA 70B QLoRA GGUF?

The files are on Hugging Face in the TheBloke/ORCA_LLaMA_70B_QLoRA-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 ORCA LLaMA 70B QLoRA 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 ORCA LLaMA 70B QLoRA on 8 GB VRAM?

No, the smallest quant requires at least 32.5 GB memory at 8k context. 8 GB VRAM is insufficient.

What license does this model use?

The model is released under the llama2 license, with no warranty.

Does the model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of ORCA_LLaMA_70B_QLoRA

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other large models

All large models →