Granite 4.1 8B
Granite 4.1 8B is an open-weights language model from IBM, released April 29, 2026. It has 8.8B parameters (dense). The context window is 128K tokens.
TL;DR — Granite 4.1 is a family of dense, decoder‑only LLMs (3B, 8B, and 30B) trained on ~15T tokens using a multi‑stage pre‑training pipeline, including long‑context extension of up to 512K tokens.
Check it against your own PC →
Can you run Granite 4.1 8B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, split GPU / CPU, roughly 5 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 5.2 GB | 5.3 GB | ~5 |
| 8 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 7.2 GB | 3.3 GB | ~7 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.5 GB | – | ~29 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.5 GB | – | ~40 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.5 GB | – | ~72 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.5 GB | – | ~130 |
Ready-made quantizations on Hugging Face: ibm-granite/granite-4.1-8b-GGUF · ibm-granite/granite-4.1-8b-fp8 · unsloth/granite-4.1-8b-GGUF · bartowski/ibm-granite_granite-4.1-8b-GGUF · lmstudio-community/granite-4.1-8b-GGUF · mradermacher/granite-4.1-8b-i1-GGUF
Benchmark results
Epoch AI has not published results for Granite 4.1 8B yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: ibm-granite/granite-4.1-8b
More from IBM
granite switch 4.1 8b · granite switch 4.1 30b · Granite 4.1 30B · Granite-4.0-H-Tiny · Granite-4.0-H-Micro · Granite-4.0-H-Small · Granite-Docling