// InternLM / Intern-S · Vision-language
Intern-S1-mini: VRAM & local deployment
8.54B parameters. About 7.4 GB at 4-bit and 20.5 GB at BF16 with one 8K-token request.
released 2025-08-18licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Shanghai AI Lab · internlm |
|---|---|
| Family / series | InternLM / Intern-S · Intern-S1-mini |
| Type | Vision-language (image-text-to-text) |
| Parameters | 8.54B Source: counted from official safetensors weights |
| Context length | 64K tokens (65,536)max_position_embeddings in config.json |
| Architecture | 36 layers · GQA |
| Released weights | BF16 · 17.1 GBdownload |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-08-18 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Smallest GPU | Mac |
|---|---|---|---|---|---|
| BF16 / FP16 (original) | 17.1 GB | 20.5 GB | 24.1 GB | RTX 4090 24GB | Mac 36GB |
| FP8 / INT8 / Q8_0 | 9.1 GB | 11.7 GB | 15.3 GB | 16GB GPU | Mac 24GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 5.2 GB | 7.4 GB | 11.0 GB | 12GB GPU | Mac 16GB |
KV cache per request: 8K 1.2 GB · 32K 4.8 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- SGLang — mentioned in the official model card
- Ollama — mentioned in the official model card
- Transformers — mentioned in the official model card
- LMDeploy — mentioned in the official model card
- llama.cpp — official GGUF weights
04Official repositories & quantised builds
3 official repo(s) from internlm.
- Intern-S1-mini main
- Intern-S1-mini-FP8 FP8
- Intern-S1-mini-GGUF GGUF
05Other InternLM / Intern-S models
All 12 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| Intern-S2-397B | 403.4B | 270 GB | 2026-09-13 |
| Atria-Dawn-Preview | 753.3B | 504 GB | 2026-09-11 |
| Intern-S2-Mobius | 36B | 24.7 GB | 2026-07-29 |
| Intern-S2-Preview | 36.1B | 24.7 GB | 2026-05-15 |
| Intern-S1-Pro | 1T / 22B | 669 GB | 2026-02-02 |
| Intern-S1 | 240.7B | 163 GB | 2025-07-24 |
| internlm3-8b-instruct | 8.8B | 6.8 GB | 2025-01-13 |
| internlm2_5-1_8b-chat | 1.89B | 2.6 GB | 2024-07-30 |
06Sources
Data checked 2026-03-29. Parameters, context and licence are copied from the official repository; memory figures are our estimates.