Granite 4.0 Micro — Hardware Requirements & GPU Compatibility
Chat
Granite 4.0 Micro is a 3.4B-parameter open language model from IBM. It supports a context window of up to 131,072 tokens. At BF16 it needs about 7.27 GB of VRAM — see which GPUs and Macs can run it below.
169.0K downloads
273 likesSpecifications
- Publisher
- IBM
- Parameters
- 3.4B
- Architecture
- GraniteMoeHybridForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 100,352
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Granite 4.0 Micro Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 7.3 GB | 17.8 GB | 6.81 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Granite 4.0 Micro?
BF16 · 7.3 GBGranite 4.0 Micro (BF16) requires 7.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 10+ GB is recommended. Using the full 131K context window can add up to 10.6 GB, bringing total usage to 17.8 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080.
Runs great
— Plenty of headroom
Which Devices Can Run Granite 4.0 Micro?
BF16 · 7.3 GB33 devices with unified memory can run Granite 4.0 Micro, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Granite 4.0 Micro need?
Granite 4.0 Micro requires 7.3 GB of VRAM at BF16. Full 131K context adds up to 10.6 GB (17.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.4B × 16 bits ÷ 8 = 6.8 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 11 GB (at full 131K context)
VRAM usage by quantization
BF167.3 GBBF16 + full context17.8 GB- Can I run Granite 4.0 Micro on a Mac?
Granite 4.0 Micro requires at least 7.3 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 4.0 Micro locally?
Yes — Granite 4.0 Micro can run locally on consumer hardware. At BF16 quantization it needs 7.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Granite 4.0 Micro?
At BF16, Granite 4.0 Micro can reach ~401 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~90 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 ÷ 7.3 × 0.55 = ~401 tok/s
Estimated speed at BF16 (7.3 GB)
~401 tok/s~90 tok/s~300 tok/s~248 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Granite 4.0 Micro?
At BF16, the download is about 6.81 GB.
- Which GPUs can run Granite 4.0 Micro?
35 consumer GPUs can run Granite 4.0 Micro at BF16 (7.3 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 27 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Granite 4.0 Micro?
33 devices with unified memory can run Granite 4.0 Micro at BF16 (7.3 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.