// InternLM / Intern-S · Text LLM
internlm2_5-7b-chat: VRAM & local deployment
7.74B parameters. About 6.7 GB at 4-bit and 18.6 GB at BF16 with one 8K-token request.
released 2024-06-27licence: Custom licence – read itmemory figures are estimates
01Specs
| Publisher | Shanghai AI Lab · internlm |
|---|---|
| Family / series | InternLM / Intern-S · internlm2_5 |
| Type | Text LLM (text-generation) |
| Parameters | 7.74B Source: counted from official safetensors weights |
| Context length | 32K tokens (32,768)max_position_embeddings in config.json |
| Architecture | 32 layers · GQA |
| Released weights | BF16 · 15.5 GBdownload |
| Licence | other · Custom licence – read itThe publisher uses its own licence; we have not classified it. Read the licence text. |
| Released | 2024-06-27 (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) | 15.5 GB | 18.6 GB | 21.8 GB | RTX 4090 24GB | Mac 36GB |
| FP8 / INT8 / Q8_0 | 8.2 GB | 10.6 GB | 13.8 GB | 12GB GPU | Mac 24GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 4.7 GB | 6.7 GB | 9.9 GB | 8GB GPU | Mac 16GB |
KV cache per request: 8K 1.1 GB · 32K 4.3 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
- llama.cpp — mentioned in the official model card
- Transformers — mentioned in the official model card
- LMDeploy — mentioned in the official model card
04Official repositories & quantised builds
4 official repo(s) from internlm.
- internlm2_5-7b-chat Instruct
- internlm2_5-7b main
- internlm2_5-7b-chat-gguf Instruct/GGUF
- internlm2_5-7b-chat-4bit Instruct
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-mini | 8.54B | 7.4 GB | 2025-08-18 |
| Intern-S1 | 240.7B | 163 GB | 2025-07-24 |
| internlm3-8b-instruct | 8.8B | 6.8 GB | 2025-01-13 |
06Sources
Data checked 2025-03-13. Parameters, context and licence are copied from the official repository; memory figures are our estimates.