granite switch 4.1 8b
granite switch 4.1 8b is an open-weights language model from IBM, released October 14, 2026. It has 8.8B parameters (dense). The context window is 128K tokens.
Check it against your own PC →
Can you run granite switch 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 | 5.4 GB | ~5 |
| 8 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 7.2 GB | 3.4 GB | ~7 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.6 GB | – | ~29 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.6 GB | – | ~40 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.6 GB | – | ~72 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.6 GB | – | ~130 |
Ready-made quantizations on Hugging Face: ibm-granite/granite-switch-4.1-8b-GGUF · netprojects/granite-switch-4.1-8b-mlx-8bit · netprojects/granite-switch-4.1-8b-mlx-4bit
Benchmark results
Epoch AI has not published results for granite switch 4.1 8b yet. New models are usually evaluated within days to weeks.
Links
Hugging Face: ibm-granite/granite-switch-4.1-8b
More from IBM
granite switch 4.1 30b · Granite 4.1 30B · Granite 4.1 8B · Granite-4.0-H-Tiny · Granite-4.0-H-Micro · Granite-4.0-H-Small · Granite-Docling