S1

S1 VL 32B

GGUFGGUF by mradermacherUpdated 2026-10-17
Download on Hugging Face
Parameters32.8B
Context256K
Layers64
Architectureqwen3vl
Smallest quant12.3 GB
Quick answer

S1 VL 32B needs about 22.4 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 12.3 GB (Q2_K) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

S1 VL 32B – 32.8B parameter multimodal model for scientific reasoning

S1 VL 32B is a 32.8B parameter multimodal large language model built on qwen3vl architecture. It supports scientific reasoning and image‑based tool invocation. The model was trained on 262144 context tokens and released under apache-2.0 license.

Good at

  • Scientific multimodal reasoning
  • Image tool invocation
  • Complex multi‑step problem solving

Limits

  • No vision support beyond image tools
  • Large VRAM requirement for higher quants
  • Limited to 262144 context tokens

Best for

  • Academic figure Q&A
  • Medical image analysis
  • Chemical structure recognition

Who it’s for. Researchers and developers needing advanced scientific multimodal reasoning. The model is suitable for applications that require chain‑of‑thought reasoning and image manipulation via code tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.3 GB 15.0 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
Q3_K_M16.0 GB 18.6 GB
Too big Get file →
Q3_K_L17.3 GB 20.0 GB
Too big Get file →
IQ4_XS17.9 GB 20.5 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.8 GB 22.4 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.2 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →
Q8_034.8 GB 37.5 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (12.34 GB) or Q3_K_S (14.39 GB). For 16 GB VRAM, Q4_K_S (18.77 GB) or Q4_K_M (19.76 GB) are suitable. Larger quants such as Q5_K_M or Q6_K require 25–30 GB VRAM and are recommended only for high‑end GPUs.

What GPU do you need for S1 VL 32B?

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: the best quant that fits is Q2_K (12.3 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.8 GB file, about 22.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).

Which S1 VL 32B quant should you choose?

Q4_K_M is the usual starting point for S1 VL 32B: it balances file size and quality well. Here it is a 19.8 GB file.

The Q8_0 file is 34.8 GB, about 1.8 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 Q2_K at 12.3 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

Architectureqwen3vl
Parameters32.8B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)2,730
Last updated2026-10-17

Frequently asked questions about S1 VL 32B

How much VRAM does S1 VL 32B need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 19.8 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 S1 VL 32B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of S1 VL 32B GGUF?

It depends on the quant: Q2_K is 12.3 GB, Q3_K_S is 14.4 GB, Q3_K_M is 16.0 GB, Q3_K_L is 17.3 GB, IQ4_XS is 17.9 GB, Q4_K_S is 18.8 GB and 5 more.

What context length does S1 VL 32B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 S1 VL 32B GGUF?

The files are on Hugging Face in the mradermacher/S1-VL-32B-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 S1 VL 32B 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 S1 VL 32B on 8 GB VRAM?

Use the Q2_K or Q3_K_S quant, which are 12.34 GB and 14.39 GB respectively and fit within 8 GB VRAM with some swapping.

Does the model support vision tasks?

It supports image tool invocation but does not have native vision inference beyond that.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of S1-VL-32B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other medium models

All medium models →