Meditron3 70B — Hardware Requirements & GPU Compatibility
Chat
Meditron3 70B is a 70.6B-parameter open language model from EPFLiGHT. At BF16 it needs about 155.22 GB of VRAM — see which GPUs and Macs can run it below.
5.3K downloads
26 likesSpecifications
- Publisher
- EPFLiGHT
- Parameters
- 70.6B
- Release Date
- 2024-07-12
Get Started
HuggingFace
How Much VRAM Does Meditron3 70B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 155.2 GB | — | 141.11 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Meditron3 70B?
BF16 · 155.2 GBMeditron3 70B (BF16) requires 155.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 202+ GB is recommended. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Meditron3 70B?
BF16 · 155.2 GB6 devices with unified memory can run Meditron3 70B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 256GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Meditron3 70B need?
Meditron3 70B requires 155.2 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 70.6B × 16 bits ÷ 8 = 141.1 GB
KV Cache + Overhead ≈ 14.1 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF16155.2 GB- Can NVIDIA GeForce RTX 5090 run Meditron3 70B?
No — Meditron3 70B requires at least 155.2 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Meditron3 70B on a Mac?
Meditron3 70B requires at least 155.2 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 Meditron3 70B locally?
Yes — Meditron3 70B can run locally on consumer hardware. At BF16 quantization it needs 155.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Meditron3 70B?
At BF16, Meditron3 70B can reach ~28 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 155.2 × 0.65 = ~34 tok/s
Estimated speed at BF16 (155.2 GB)
~34 tok/s~34 tok/s~28 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Meditron3 70B?
At BF16, the download is about 141.11 GB.
- Which GPUs can run Meditron3 70B?
No single consumer GPU has enough VRAM to run Meditron3 70B at BF16 (155.2 GB). Multi-GPU or professional hardware is required.
- Which devices can run Meditron3 70B?
6 devices with unified memory can run Meditron3 70B at BF16 (155.2 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.