Skip to content
English

Switch theme

// IBM Granite · Speech-to-text

granite-speech-4.1-2b-plus: VRAM & local deployment

2.11B parameters. About 1.9 GB at 4-bit and 5.1 GB at BF16.

released 2026-04-16licence: Commercial OKmemory figures are estimates

01Specs

PublisherIBM · ibm-granite
Family / seriesIBM Granite · granite-speech-4.1-plus
TypeSpeech-to-text (automatic-speech-recognition)
Parameters2.11B Source: counted from official safetensors weights
Released weightsBF16 · 4.2 GBdownload
LicenceApache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed.
Released2026-04-16 (Hugging Face repo created)

02How much VRAM it needs (estimate)

Speech models are small; the weight size is close to the total memory needed.

PrecisionWeightsWeights + overheadSmallest GPUMac
BF16 / FP16 (original)4.2 GB 5.1 GB 8GB GPUMac 16GB
FP8 / INT8 / Q8_02.2 GB 3.0 GB 8GB GPUMac 16GB
4-bit (Q4_K_M / AWQ / GPTQ-Int4)1.3 GB 1.9 GB 8GB GPUMac 16GB

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

2 official repo(s) from ibm-granite.

05Other IBM Granite models

All 67 →
ModelParams4-bit totalReleased
granite-switch-4.1-8b8.78B7.8 GB2026-10-14
granite-switch-4.1-30b30B22.7 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

06Sources

Data checked 2026-10-21. Parameters, context and licence are copied from the official repository; memory figures are our estimates.

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