IN

Intern S1

InternLMGGUF by bartowskiUpdated 2025-08-14
Download on Hugging Face
Parameters235B
Context40K
Layers94
Architectureqwen3moe
Smallest quant0.5 GB
Quick answer

Intern S1 needs about 144.7 GB of memory at Q4_K_M (a 142.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 22 quants, from 0.5 GB to 250.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

Intern S1 – a 235B multimodal model with vision and language capabilities

Intern S1 is a 235B MoE language model with a 6B vision encoder. It supports multimodal reasoning and is trained on 5 trillion tokens, including 2.5 trillion scientific-domain tokens. The model is released under Apache‑2.0.

Good at

  • Multimodal reasoning
  • Scientific domain tasks
  • Vision‑language benchmarks

Limits

  • Requires large VRAM for high‑quality quants
  • No native prompt format specified
  • Limited to 40960 context tokens

Best for

  • Research assistants in chemistry and biology
  • Scientific data analysis
  • Complex vision‑language queries

Who it’s for. Researchers, data scientists, and developers needing a large multimodal model for scientific applications. The model is open‑source and can be run locally with llama.cpp or similar projects.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 2.6 GB
Fits Get file →
IQ2_XS65.6 GB (2 parts) 67.7 GB
Too big Get file →
IQ2_S66.1 GB (2 parts) 68.2 GB
Too big Get file →
Q2_K82.7 GB (3 parts) 84.8 GB
Too big Get file →
Q2_K_L83.3 GB (3 parts) 85.4 GB
Too big Get file →
IQ3_XXS93.1 GB (3 parts) 95.2 GB
Too big Get file →
IQ3_XS96.9 GB (3 parts) 99.0 GB
Too big Get file →
Q3_K_S102.4 GB (3 parts) 104.5 GB
Too big Get file →
IQ3_M107.3 GB (3 parts) 109.4 GB
Too big Get file →
Q3_K_M107.3 GB (3 parts) 109.4 GB
Too big Get file →
Q3_K_L111.2 GB (3 parts) 113.3 GB
Too big Get file →
Q3_K_XL111.7 GB (3 parts) 113.8 GB
Too big Get file →
IQ4_XS125.9 GB (4 parts) 128.0 GB
Too big Get file →
IQ4_NL133.1 GB (4 parts) 135.2 GB
Too big Get file →
Q4_0135.0 GB (4 parts) 137.1 GB
Too big Get file →
Q4_K_S137.7 GB (4 parts) 139.8 GB
Too big Get file →
Q4_K_M142.7 GB (4 parts) 144.7 GB
Too big Get file →
Q4_1147.3 GB (4 parts) 149.4 GB
Too big Get file →
Q5_K_S162.0 GB (5 parts) 164.0 GB
Too big Get file →
Q5_K_M166.9 GB (5 parts) 169.0 GB
Too big Get file →
Q6_K193.1 GB (5 parts) 195.1 GB
Too big Get file →
Q8_0250.0 GB (7 parts) 252.0 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XS or IQ2_S quants (≈67 GB memory at 8 k context). For 16 GB VRAM, Q4_0 or Q4_K_S are suitable (≈137 GB memory). For 32 GB VRAM, Q5_K_M or Q6_K provide higher quality with manageable memory usage.

What GPU do you need for Intern S1?

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: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).

Which Intern S1 quant should you choose?

Q4_K_M is the usual starting point for Intern S1: it balances file size and quality well. Here it is a 142.7 GB file.

The Q8_0 file is 250.0 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 the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters235B (approximate, mixture of experts)
Layers94
Trained context40,960 tokens
KV cache (fp16)188 KB per token

Source

Quantized bybartowski
FamilyInternLM
Licenseapache-2.0
Downloads (HF)741
Last updated2025-08-14

Frequently asked questions about Intern S1

How much VRAM does Intern S1 need?

About 144.7 GB at Q4_K_M with an 8K context window. That is the 142.7 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 on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Intern S1 GGUF?

It depends on the quant: file is 0.5 GB, IQ2_XS is 65.6 GB, IQ2_S is 66.1 GB, Q2_K is 82.7 GB, Q2_K_L is 83.3 GB, IQ3_XXS is 93.1 GB and 16 more.

What context length does Intern S1 support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.

Where can I download Intern S1 GGUF?

The files are on Hugging Face in the bartowski/internlm_Intern-S1-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 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 on 8 GB VRAM?

Use the IQ2_XS or IQ2_S quantized files; they require about 67 GB of memory at 8 k context, which is beyond 8 GB VRAM, so it is not feasible.

Does Intern S1 support vision tasks?

Yes, Intern S1 includes a 6B vision encoder and supports multimodal reasoning.

Other GGUFs of Intern-S1

Similar models

Browse all →

More from bartowski

All by bartowski →

More InternLM models

All InternLM →

Other large models

All large models →