MAI DS R1 FP8 — Hardware Requirements & GPU Compatibility
ChatReasoning
568 downloads
25 likesSpecifications
- Publisher
- Microsoft
- Parameters
- 671.1B
- Architecture
- DeepseekV3ForCausalLM
- Context Length
- 163,840 tokens
- Vocabulary Size
- 129,280
- Release Date
- 2025-12-15
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does MAI DS R1 FP8 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 1346.0 GB | 1629.0 GB | 1342.13 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run MAI DS R1 FP8?
BF16 · 1346.0 GBMAI DS R1 FP8 (BF16) requires 1346.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1750+ GB is recommended. Using the full 164K context window can add up to 283.0 GB, bringing total usage to 1629.0 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Related Models
Frequently Asked Questions
- How much VRAM does MAI DS R1 FP8 need?
MAI DS R1 FP8 requires 1346.0 GB of VRAM at BF16. Full 164K context adds up to 283.0 GB (1629.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 671.1B × 16 bits ÷ 8 = 1342.1 GB
KV Cache + Overhead ≈ 3.9 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 286.9 GB (at full 164K context)
VRAM usage by quantization
BF161346.0 GBBF16 + full context1629.0 GB- Can NVIDIA GeForce RTX 5090 run MAI DS R1 FP8?
No — MAI DS R1 FP8 requires at least 1346.0 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run MAI DS R1 FP8 on a Mac?
MAI DS R1 FP8 requires at least 1346.0 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 MAI DS R1 FP8 locally?
Yes — MAI DS R1 FP8 can run locally on consumer hardware. At BF16 quantization it needs 1346.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of MAI DS R1 FP8?
At BF16, the download is about 1342.13 GB.
- Which GPUs can run MAI DS R1 FP8?
No single consumer GPU has enough VRAM to run MAI DS R1 FP8 at BF16 (1346.0 GB). Multi-GPU or professional hardware is required.
- Which devices can run MAI DS R1 FP8?
MAI DS R1 FP8 requires at least 1346.0 GB at BF16, which exceeds the unified memory of most consumer devices. A high-memory Mac Studio, Mac Pro, or multi-GPU desktop setup is recommended.