Can I run Intern S1 Pro locally?
Intern S1 Pro by internlm has 917B parameters (23B active per token, 512 experts, 8 used per token). At 4-bit with an 8K context it needs about 524 GB of GPU memory. It fits on 1 of 65 GPUs and Macs we track.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx | 128K ctx |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | rough | 322 GB | 322 GB | 327 GB | 344 GB |
| 3-bit (Q3_K_M) | usable | 419 GB | 420 GB | 424 GB | 442 GB |
| 4-bit (Q4_K_M) | good, most popular | 523 GB | 524 GB | 529 GB | 546 GB |
| 5-bit (Q5_K_M) | very good | 610 GB | 611 GB | 615 GB | 633 GB |
| 6-bit (Q6_K) | near lossless | 702 GB | 702 GB | 707 GB | 725 GB |
| 8-bit (Q8_0) | effectively lossless | 909 GB | 910 GB | 914 GB | 932 GB |
| 16-bit (F16/BF16) | original weights | 1710 GB | 1710 GB | 1715 GB | 1732 GB |
Which GPUs and Macs run Intern S1 Pro?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
Questions
How much VRAM does Intern S1 Pro need?
About 524 GB at 4-bit (Q4_K_M) with an 8K context: 522 GB of weights (estimated), 1.5 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 910 GB.
What is the smallest GPU that runs Intern S1 Pro?
No single consumer GPU in our table fits it at Q4_K_M with 8K context.
Can I run Intern S1 Pro on a Mac?
Not at Q4_K_M with 8K context on any Mac in our table, even a 512 GB Mac Studio, using the default GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
Intern S1
241B · 139 GB at 4-bitInternLM3 8B Instruct
8.8B · 6.0 GB at 4-bitInternLM2.5 7B Chat
7.7B · 6.0 GB at 4-bitInkling
952B · 545 GB at 4-bitLing 1T
1000B · 570 GB at 4-bitMuse Spark Open 816B A42B
822B · 470 GB at 4-bitEmbed this
Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.
Copy a snippet
Markdown badge
[](https://runsonmy.com/model/intern-s1-pro/) Widget (script)
<div class="runsonmy-widget" data-model="intern-s1-pro"><a href="https://runsonmy.com/model/intern-s1-pro/">Will Intern S1 Pro run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script> Widget (iframe)
<iframe src="https://runsonmy.com/embed/m/intern-s1-pro/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Intern S1 Pro run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | internlm/Intern-S1-Pro |
| Parameters | 917,044,193,560 (917B) · ~23B active (computed from config), low confidence, speed not shown |
| Layers / hidden size | 94 / 4096 |
| Attention | GQA; 64 heads, 4 KV heads, head dim 128 |
| KV cache per token (FP16) | 188.0 KiB |
| Max context | 262,144 tokens |
| License | apache-2.0 |
| Released on HF | Feb 2, 2026 |
| Downloads (30d) / likes | 10,565 / 277 |
Sources: Hugging Face model API · config.json (internlm/Intern-S1-Pro) · GPU specs from vendor pages (list). Data fetched Nov 18, 2026. Spot an error? Report it.