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.
Meditron3 70B runs on a 192 GB+ Mac or a datacenter GPU
Best local pick → Mac Pro M2 Ultra (192 GB) · BF16 · 159.9 GB · ~4 tok/s
Macs from 192 GB (BF16 · ~4 tok/s)
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Meditron3 70B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve EPFLiGHT/Meditron3-70B --max-model-len 16384 --tensor-parallel-size 8vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on B200 (192 GB) (32 GB headroom) · BF16
- Generation speed
- ~34 tok/s
- generation speed
- Cost per 1M output tokens
- $49.59
- per 1M output tokens
How Much VRAM Does Meditron3 70B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 155.2 GB | 165.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on B200 192 GB |
Selected BF16
Brain floating point 16159.9GBat 16K context
- Weights
- 154.3 GB
- KV cache
- 5.4 GB
- Overhead
- 0.3 GB
Server-class: ~159.9 GB at 16K context · one B200 192 GB
Which Hardware 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 consumer GPU has enough memory. 4 devices with unified memory can run Meditron3 70B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Pro M2 Ultra (192 GB).
192+ GB
fits · 32.1 GB free · up to 32K ctx
6 GPUs · 1 Mac class · 2 device families
B200~34Simulate output on B200B300~34Simulate output on B300Instinct MI350X~31Simulate output on Instinct MI350XM3 Ultra256–512 GB~4Simulate output on Mac Studio (M3 Ultra, 256GB)8x H100 SXM5~112Simulate output on NVIDIA DGX H1008x A100 SXM4~68Simulate output on NVIDIA DGX A100 640GB
By VRAM tier · typical GPUs and Macs at BF16
Consumer GPUs (up to 32 GB) and Macs up to 128 GB: too small for this model (needs ≥ 159.9 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Llama 3.3 70B InstructMeta | 79.7 | 51.3 GB | —needs > 24 GB | same size |
| NVIDIA Nemotron 3.5 Bolt 74B A9B BF16NVIDIA | — | 54.2 GB | —needs > 24 GB | same size |
| Qwen2.5 VL 72B InstructAlibaba | — | 49.7 GB | —needs > 24 GB | same size |
| Qwen2 VL 72B InstructAlibaba | — | 49.7 GB | —needs > 24 GB | same size |
| Qwen1.5 72B ChatAlibaba | — | 86.6 GB | —needs > 24 GB | same size |
| CodeLlama 70B Instruct HFMeta | — | 23.2 GB | ~29 | same size |
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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
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?
Yes — Mac Pro M2 Ultra (192 GB) and 3 other Macs can run Meditron3 70B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 155.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run Meditron3 70B locally?
Yes — Meditron3 70B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Meditron3 70B?
At BF16, Meditron3 70B can reach ~31 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)
Real-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?
4 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.