Granite Switch 4.1 8B Preview — Hardware Requirements & GPU Compatibility
Chat
Granite Switch 4.1 8B Preview is a 9.6B-parameter open language model from IBM. It supports a context window of up to 131,072 tokens. At BF16 it needs about 19.78 GB of VRAM — see which GPUs and Macs can run it below.
605 downloads
25 likesSpecifications
- Publisher
- IBM
- Parameters
- 9.6B
- Architecture
- GraniteSwitchForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 100,364
- Release Date
- 2026-05-24
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Granite Switch 4.1 8B Preview Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 19.8 GB | 41.5 GB | 19.14 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Granite Switch 4.1 8B Preview?
BF16 · 19.8 GBGranite Switch 4.1 8B Preview (BF16) requires 19.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ GB is recommended. Using the full 131K context window can add up to 21.7 GB, bringing total usage to 41.5 GB. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Granite Switch 4.1 8B Preview?
BF16 · 19.8 GB21 devices with unified memory can run Granite Switch 4.1 8B Preview, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Granite Switch 4.1 8B Preview need?
Granite Switch 4.1 8B Preview requires 19.8 GB of VRAM at BF16. Full 131K context adds up to 21.7 GB (41.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 9.6B × 16 bits ÷ 8 = 19.1 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 22.4 GB (at full 131K context)
VRAM usage by quantization
BF1619.8 GBBF16 + full context41.5 GB- Can I run Granite Switch 4.1 8B Preview on a Mac?
Granite Switch 4.1 8B Preview requires at least 19.8 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Granite Switch 4.1 8B Preview locally?
Yes — Granite Switch 4.1 8B Preview can run locally on consumer hardware. At BF16 quantization it needs 19.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Granite Switch 4.1 8B Preview?
At BF16, Granite Switch 4.1 8B Preview can reach ~147 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~33 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 19.8 × 0.55 = ~147 tok/s
Estimated speed at BF16 (19.8 GB)
~147 tok/s~33 tok/s~110 tok/s~91 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Granite Switch 4.1 8B Preview?
At BF16, the download is about 19.14 GB.
- Which GPUs can run Granite Switch 4.1 8B Preview?
6 consumer GPUs can run Granite Switch 4.1 8B Preview at BF16 (19.8 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Granite Switch 4.1 8B Preview?
21 devices with unified memory can run Granite Switch 4.1 8B Preview at BF16 (19.8 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.