P1

P1 VL 235B A22B

GGUFGGUF by axi0mXUpdated 2026-05-28
Download on Hugging Face
Parameters235B
Context256K
Layers94
Architectureqwen3vlmoe
Smallest quant54.7 GB
Quick answer

P1 VL 235B A22B needs about 144.2 GB of memory at Q4_K_M (a 142.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 17 quants, from 54.7 GB (TQ1_0) to 265.1 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

P1 VL 235B A22B – high‑performance vision‑language model for physics reasoning

P1 VL 235B A22B is a 235 billion‑parameter vision‑language model built on Qwen3‑VL. It excels at physics Olympiad tasks, achieving No.3 on HiPhO and gold‑tier performance on IPhO 2025. The model supports reasoning, tools, and vision.

Good at

  • Physics diagram reasoning
  • Multimodal STEM tasks
  • Large‑context inference

Limits

  • Requires 262144 context tokens
  • No vision support beyond image input
  • Apache‑2.0 license restricts commercial use

Best for

  • Physics competition prep
  • Scientific diagram analysis
  • Educational content generation

Who it’s for. Researchers and educators needing a physics‑focused multimodal model. Developers can integrate it into applications that require diagram‑to‑logic translation and large‑context reasoning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_054.7 GB 56.8 GB
Too big Get file →
IQ1_S63.0 GB 65.1 GB
Too big Get file →
IQ1_M69.7 GB 71.8 GB
Too big Get file →
IQ2_M84.1 GB 86.1 GB
Too big Get file →
Q2_K_XL88.1 GB 90.2 GB
Too big Get file →
IQ3_XXS94.7 GB 96.8 GB
Too big Get file →
IQ3_S103.3 GB 105.4 GB
Too big Get file →
Q3_K_XL103.8 GB 105.9 GB
Too big Get file →
Q3_K_M112.4 GB 114.5 GB
Too big Get file →
IQ4_XS125.3 GB 127.4 GB
Too big Get file →
IQ4_NL132.6 GB 134.7 GB
Too big Get file →
Q4_K_XL134.2 GB 136.3 GB
Too big Get file →
Q4_K_M142.2 GB 144.2 GB
Too big Get file →
Q5_K_XL166.9 GB 169.0 GB
Too big Get file →
Q6_K_XL198.9 GB 200.9 GB
Too big Get file →
Q8_0249.9 GB 252.0 GB
Too big Get file →
Q8_K_XL265.1 GB 267.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (142.15 GB file, 144.2 GB memory). For 16 GB VRAM, Q4_K_XL (134.22 GB file, 136.3 GB memory) is suitable. Higher‑precision quants like Q8_0 exceed typical VRAM limits.

What GPU do you need for P1 VL 235B A22B?

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 P1 VL 235B A22B quant should you choose?

Q4_K_M is the usual starting point for P1 VL 235B A22B: it balances file size and quality well. Here it is a 142.2 GB file.

The Q8_0 file is 249.9 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 TQ1_0 at 54.7 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3vlmoe
Parameters235B (approximate, mixture of experts)
Active parameters22B
Layers94
Trained context262,144 tokens
KV cache (fp16)188 KB per token

Source

Quantized byaxi0mX
Licenseapache-2.0
Downloads (HF)826
Last updated2026-05-28

Frequently asked questions about P1 VL 235B A22B

How much VRAM does P1 VL 235B A22B need?

About 144.2 GB at Q4_K_M with an 8K context window. That is the 142.2 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 P1 VL 235B A22B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 56.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of P1 VL 235B A22B GGUF?

It depends on the quant: TQ1_0 is 54.7 GB, IQ1_S is 63.0 GB, IQ1_M is 69.7 GB, IQ2_M is 84.1 GB, Q2_K_XL is 88.1 GB, IQ3_XXS is 94.7 GB and 11 more.

What context length does P1 VL 235B A22B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.

Where can I download P1 VL 235B A22B GGUF?

The files are on Hugging Face in the axi0mX/P1-VL-235B-A22B-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 P1 VL 235B A22B 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 P1 VL 235B A22B on 8 GB VRAM?

No, the smallest quant requires more than 8 GB VRAM. Use a larger GPU or a lower‑precision quant if available.

Does the model support image input?

Yes, it is a vision‑language model and accepts image data for reasoning tasks.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of P1-VL-235B-A22B

Similar models

Browse all →

More from axi0mX

All by axi0mX →

Other large models

All large models →