// rednote dots · Text LLM
dots.llm1.base: VRAM & local deployment
142B total · 14B active (MoE) parameters. About 104 GB at 4-bit and 321 GB at BF16 with one 8K-token request.
released 2026-10-06licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | rednote hi lab · rednote-hilab |
|---|---|
| Family / series | rednote dots · dots.llm1.base |
| Type | Text LLM (text-generation) |
| Parameters | 142B total · 14B active (MoE) Source: official model card“activates 14B parameters out of a total of 142B parameters” |
| Context length | 32K tokens (32,768)max_position_embeddings in config.json |
| Architecture | 62 layers · GQA · MoE |
| Released weights | FP32 · 6.2 GBdownload |
| Licence | MIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2026-10-06 (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) | 284 GB | 321 GB | 346 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB |
| FP8 / INT8 / Q8_0 | 151 GB | 175 GB | 200 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 86.1 GB | 104 GB | 128 GB | H200 141GB | Mac 256GB |
KV cache per request: 8K 8.3 GB · 32K 33.3 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
- SGLang — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
1 official repo(s) from rednote-hilab.
- dots.llm1.base Base
06Sources
Data checked 2026-10-07. Parameters, context and licence are copied from the official repository; memory figures are our estimates.