IN

Intern-S1-Mini

InternLMGGUF by internlmUpdated 2025-08-19
Download on Hugging Face
Parameters8.2B
Context40K
Layers36
Architectureqwen3
Smallest quant8.7 GB
Quick answer

Intern-S1-Mini needs about 10.4 GB of memory at Q8_0 (a 8.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.7 GB (Q8_0) to 16.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Intern-S1-mini: 8.2B multimodal model with strong scientific reasoning

Intern-S1-mini is an 8.2B dense language model based on Qwen3 with a 0.3B vision encoder. It is pretrained on 5 trillion multimodal tokens, including 2.5 trillion scientific-domain tokens. The model excels at interpreting chemical structures, protein sequences, and planning compound synthesis routes.

Good at

  • Scientific multimodal reasoning
  • Chemical structure interpretation
  • Protein sequence understanding

Limits

  • No vision support in llama.cpp by default
  • Requires at least 10.4GB VRAM for Q8_0
  • Large context length of 40960 tokens

Best for

  • Research assistants in chemistry
  • Bioinformatics data analysis
  • Scientific literature summarization

Who it’s for. Developers and researchers needing a lightweight multimodal model for scientific tasks. The model is open‑source under Apache‑2.0 and can be deployed locally with llama.cpp or other inference frameworks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_08.7 GB 10.4 GB
Too big Get file →
F1616.4 GB 18.1 GB
Too big Get file →

For 8‑GB VRAM, use Q8_0 which requires 10.4GB memory at 8k context – this is slightly above the limit, so a GPU with 12‑GB or more is recommended. For larger GPUs, the F16 quantization uses 18.1GB memory at 8k context and offers higher precision.

What GPU do you need for Intern-S1-Mini?

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 Q8_0 (8.7 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.4 GB file, about 18.1 GB in use).

Which Intern-S1-Mini quant should you choose?

Q8_0 (8.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters8.2B
Layers36
Trained context40,960 tokens
KV cache (fp16)144 KB per token

Source

Quantized byinternlm
FamilyInternLM
Licenseapache-2.0
Downloads (HF)2,333
Last updated2025-08-19

Frequently asked questions about Intern-S1-Mini

How much VRAM does Intern-S1-Mini need?

About 10.4 GB at Q8_0 with an 8K context window. That is the 8.7 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 Intern-S1-Mini on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Intern-S1-Mini GGUF?

It depends on the quant: Q8_0 is 8.7 GB, F16 is 16.4 GB.

What context length does Intern-S1-Mini support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Intern-S1-Mini GGUF?

The files are on Hugging Face in the internlm/Intern-S1-mini-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 Intern-S1-Mini 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 Intern-S1-mini on 8 GB VRAM?

The Q8_0 quantization requires 10.4GB memory at 8k context, so 8GB VRAM is insufficient. A GPU with at least 12GB is recommended.

What is the context length of Intern-S1-mini?

The model supports a trained context of 40960 tokens.

Is Intern-S1-mini licensed for commercial use?

It is released under the Apache‑2.0 license, which permits commercial use.

Other GGUFs of Intern-S1-mini

Similar models

Browse all →

More from internlm

All by internlm →

More InternLM models

All InternLM →

Other small models

All small models →