Skip to content
English

Switch theme

// IBM Granite · Text LLM

granite-switch-4.1-8b: VRAM & local deployment

8.78B parameters. About 7.8 GB at 4-bit and 21.2 GB at BF16 with one 8K-token request.

released 2026-10-14licence: Commercial OKmemory figures are estimates

01Specs

PublisherIBM · ibm-granite
Family / seriesIBM Granite · granite-switch-4.1
TypeText LLM (text-generation)
Parameters8.78B Source: counted from official safetensors weights
Context length128K tokens (131,072)max_position_embeddings in config.json
Architecture42 layers · GQA
Released weightsBF16 · 17.6 GBdownload
LicenceApache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed.
Released2026-10-14 (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.

PrecisionWeightsTotal @ 8KTotal @ 32KTotal @ 128KSmallest GPUMac
BF16 / FP16 (original)17.6 GB 21.2 GB25.4 GB42.4 GB RTX 4090 24GBMac 36GB
FP8 / INT8 / Q8_09.3 GB 12.2 GB16.4 GB33.3 GB 16GB GPUMac 24GB
4-bit (Q4_K_M / AWQ / GPTQ-Int4)5.3 GB 7.8 GB12.0 GB28.9 GB 12GB GPUMac 16GB

KV cache per request: 8K 1.4 GB · 32K 5.6 GB · 128K 22.6 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.

Which inference engine to choose →

04Official repositories & quantised builds

1 official repo(s) from ibm-granite.

05Other IBM Granite models

All 67 →
ModelParams4-bit totalReleased
granite-switch-4.1-30b · same series30B22.7 GB2026-10-14
granite-speech-5.0-2b2.31B2.0 GB2026-10-07
ensemble-forecasting-with-ibm-granite-time-series——2026-10-01
granite-speech-5.0-470m-turboctc-nc473M0.8 GB2026-08-17
granite-4.2-3b3.66B3.6 GB2026-08-07
granite-4.2-8b8.79B7.7 GB2026-08-07
granite-4.2-30b29.3B22.2 GB2026-08-07
granite-speech-5.0-470m-turboctc473M0.8 GB2026-08-04
granite-embedding-97m-multilingual-r297M0.6 GB2026-04-20

06Sources

Data checked 2026-10-15. Parameters, context and licence are copied from the official repository; memory figures are our estimates.

Data updated: Self-host open models(UTC+8)