SH

shuttle 3

ShuttleGGUF by bartowskiUpdated 2024-10-29
Download on Hugging Face
Parameters72.7B
Context32K
Layers80
Architectureqwen2
Smallest quant23.7 GB
Quick answer

shuttle 3 needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 20 quants, from 23.7 GB (IQ1_M) to 77.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Shuttle‑3: 72B multilingual language model

Shuttle‑3 is a 72.7B parameter model based on Qwen‑2.5‑72b‑Instruct. It is fine‑tuned to emulate Claude‑3 prose and trained on role‑play data. The model supports a 32,768 token context window.

Good at

  • Complex chat
  • Multilingual communication
  • Reasoning and agent tasks

Limits

  • No vision support
  • Requires large VRAM for full quality
  • License is other

Best for

  • Chat applications
  • Multilingual content creation
  • AI agent development

Who it’s for. Developers needing a high‑capacity multilingual LLM for chat or agent tasks. Suitable for users with sufficient GPU memory to run the model in full quality.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M23.7 GB 26.9 GB
Too big Get file →
IQ2_XXS25.5 GB 28.7 GB
Too big Get file →
IQ2_XS27.1 GB 30.2 GB
Too big Get file →
IQ2_M29.3 GB 32.5 GB
Too big Get file →
Q2_K29.8 GB 33.0 GB
Too big Get file →
Q2_K_L31.0 GB 34.2 GB
Too big Get file →
IQ3_XXS31.8 GB 35.0 GB
Too big Get file →
Q3_K_S34.5 GB 37.7 GB
Too big Get file →
IQ3_M35.5 GB 38.7 GB
Too big Get file →
Q3_K_M37.7 GB 40.9 GB
Too big Get file →
Q3_K_L39.5 GB 42.7 GB
Too big Get file →
IQ4_XS39.7 GB 42.9 GB
Too big Get file →
Q3_K_XL40.6 GB 43.8 GB
Too big Get file →
Q4_041.4 GB 44.6 GB
Too big Get file →
Q4_K_S43.9 GB 47.1 GB
Too big Get file →
Q4_K_M47.4 GB 50.6 GB
Too big Get file →
Q5_K_S51.4 GB (2 parts) 54.6 GB
Too big Get file →
Q5_K_M54.4 GB (2 parts) 57.6 GB
Too big Get file →
Q6_K64.3 GB (2 parts) 67.5 GB
Too big Get file →
Q8_077.3 GB (2 parts) 80.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (23.74 GB file, 26.9 GB memory). For 16 GB VRAM, IQ2_XS (27.06 GB file, 30.2 GB memory). For 24 GB VRAM, Q3_K_M (37.7 GB file, 40.9 GB memory).

What GPU do you need for shuttle 3?

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: the best quant that fits is IQ2_XS (27.1 GB file, about 30.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).

Which shuttle 3 quant should you choose?

Q4_K_M is the usual starting point for shuttle 3: it balances file size and quality well. Here it is a 47.4 GB file.

The Q8_0 file is 77.3 GB, about 1.6 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 IQ1_M at 23.7 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

Architectureqwen2
Parameters72.7B
Layers80
Trained context32,768 tokens
KV cache (fp16)320 KB per token

Source

Quantized bybartowski
FamilyShuttle
Licenseother
Downloads (HF)1,335
Last updated2024-10-29

Frequently asked questions about shuttle 3

How much VRAM does shuttle 3 need?

About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 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 shuttle 3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of shuttle 3 GGUF?

It depends on the quant: IQ1_M is 23.7 GB, IQ2_XXS is 25.5 GB, IQ2_XS is 27.1 GB, IQ2_M is 29.3 GB, Q2_K is 29.8 GB, Q2_K_L is 31.0 GB and 14 more.

What context length does shuttle 3 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download shuttle 3 GGUF?

The files are on Hugging Face in the bartowski/shuttle-3-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 shuttle 3 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 Shuttle‑3 on 8 GB VRAM?

Yes, using the IQ1_M quantization which requires about 26.9 GB of memory at 8k context.

Does Shuttle‑3 support vision?

No, the model has no vision capabilities.

What is the context length of Shuttle‑3?

The model supports a 32,768 token context window.

Other GGUFs of shuttle-3

Similar models

Browse all →

More from bartowski

All by bartowski →

More Shuttle models

All Shuttle →

Other large models

All large models →