// IBM Granite · Text LLM
granite-4.0-350m: VRAM & local deployment
352M parameters. About 1.0 GB at 4-bit and 1.5 GB at BF16 with one 8K-token request.
released 2025-10-07licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | IBM · ibm-granite |
|---|---|
| Family / series | IBM Granite · granite-4.0 |
| Type | Text LLM (text-generation) |
| Parameters | 352M Source: counted from official safetensors weights |
| Context length | 32K tokens (32,768)max_position_embeddings in config.json |
| Architecture | 28 layers · GQA |
| Released weights | BF16 · 0.7 GBdownload |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-10-07 (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) | 0.7 GB | 1.5 GB | 2.2 GB | 8GB GPU | Mac 16GB |
| FP8 / INT8 / Q8_0 | 0.4 GB | 1.1 GB | 1.8 GB | 8GB GPU | Mac 16GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 0.2 GB | 1.0 GB | 1.7 GB | 8GB GPU | Mac 16GB |
KV cache per request: 8K 0.2 GB · 32K 0.9 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.
- Transformers — mentioned in the official model card
- llama.cpp — official GGUF weights
04Official repositories & quantised builds
4 official repo(s) from ibm-granite.
- granite-4.0-350m main
- granite-4.0-350m-GGUF GGUF
- granite-4.0-350m-base Base
- granite-4.0-350m-base-GGUF Base/GGUF
05Other IBM Granite models
All 67 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| granite-4.0-1b · same series | 1.63B | 2.3 GB | 2025-10-07 |
| granite-switch-4.1-8b | 8.78B | 7.8 GB | 2026-10-14 |
| granite-switch-4.1-30b | 30B | 22.7 GB | 2026-10-14 |
| granite-speech-5.0-2b | 2.31B | 2.0 GB | 2026-10-07 |
| ensemble-forecasting-with-ibm-granite-time-series | — | — | 2026-10-01 |
| granite-speech-5.0-470m-turboctc-nc | 473M | 0.8 GB | 2026-08-17 |
| granite-4.2-3b | 3.66B | 3.6 GB | 2026-08-07 |
| granite-4.2-8b | 8.79B | 7.7 GB | 2026-08-07 |
| granite-4.2-30b | 29.3B | 22.2 GB | 2026-08-07 |
06Sources
Data checked 2025-10-23. Parameters, context and licence are copied from the official repository; memory figures are our estimates.