SK

Sky T1 32B Preview

SkyGGUF by mradermacherUpdated 2025-01-13
Download on Hugging Face
Parameters32.8B
Context32K
Layers64
Architectureqwen2
Smallest quant7.3 GB
Quick answer

Sky T1 32B Preview needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 7.3 GB (IQ1_S) to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Sky T1 32B Preview – a 32B reasoning model with Qwen2 architecture

Sky T1 32B Preview is a 32.8B parameter model trained from Qwen2.5-32B-Instruct on 17K verified responses. It supports tool use and is licensed under apache-2.0. The model was fine‑tuned with a batch size of 96 on 8 H100 GPUs.

Good at

  • Reasoning tasks
  • Tool‑based interactions
  • Math and coding

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • No mixture of experts

Best for

  • Chatbot assistants
  • Code generation tools
  • Math problem solving

Who it’s for. Developers and researchers needing a large reasoning model that can run locally with GGUF. The model is suitable for applications that require tool integration and detailed reasoning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.3 GB 9.9 GB
Too big Get file →
IQ1_M7.9 GB 10.6 GB
Too big Get file →
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.4 GB 13.0 GB
Too big Get file →
IQ2_M11.3 GB 13.9 GB
Too big Get file →
Q2_K_S11.5 GB 14.1 GB
Too big Get file →
Q2_K12.3 GB 15.0 GB
Too big Get file →
IQ3_XXS12.8 GB 15.5 GB
Too big Get file →
IQ3_XS13.7 GB 16.4 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.4 GB 17.1 GB
Too big Get file →
IQ3_M14.8 GB 17.5 GB
Too big Get file →
Q3_K_M15.9 GB 18.6 GB
Too big Get file →
Q3_K_L17.2 GB 19.9 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.7 GB 21.4 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.9 GB 22.5 GB
Too big Get file →
Q4_120.6 GB 23.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.3 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 7.27 GB, estimated 9.9 GB memory). For 12 GB VRAM, IQ2_XS (9.96 GB, 12.6 GB memory). For 16 GB VRAM, Q3_K_S (14.39 GB, 17 GB memory). Estimates are approximate.

What GPU do you need for Sky T1 32B Preview?

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: the best quant that fits is IQ2_XXS (9.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (12.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).

Which Sky T1 32B Preview quant should you choose?

Q4_K_M is the usual starting point for Sky T1 32B Preview: it balances file size and quality well. Here it is a 19.9 GB file.

If memory is tight, the smallest file is IQ1_S at 7.3 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

Architectureqwen2
Parameters32.8B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilySky
Licenseapache-2.0
Downloads (HF)813
Last updated2025-01-13

Frequently asked questions about Sky T1 32B Preview

How much VRAM does Sky T1 32B Preview need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 Sky T1 32B Preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sky T1 32B Preview GGUF?

It depends on the quant: IQ1_S is 7.3 GB, IQ1_M is 7.9 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.4 GB, IQ2_M is 11.3 GB and 17 more.

What context length does Sky T1 32B Preview support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Sky T1 32B Preview GGUF?

The files are on Hugging Face in the mradermacher/Sky-T1-32B-Preview-i1-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 Sky T1 32B Preview use?

Hugging Face lists the license as apache-2.0. 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 Sky T1 32B Preview on 8 GB VRAM?

Use the IQ1_S quant, which requires about 9.9 GB of VRAM at 8 k context.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Sky-T1-32B-Preview

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sky models

All Sky →

Other medium models

All medium models →