Qwen2 72B Instruct FP8 — Hardware Requirements & GPU Compatibility
Chat
Qwen2 72B Instruct FP8 is a 72.7B-parameter open language model from RedHatAI in the Qwen 2 family. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 44.59 GB of VRAM — see which GPUs and Macs can run it below.
1.1K downloads
16 likesSpecifications
- Publisher
- RedHatAI
- Family
- Qwen 2
- Parameters
- 72.7B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2024-07-18
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Qwen2 72B Instruct FP8 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 31.9 GB | 41.9 GB | 30.90 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 32.8 GB | 42.9 GB | 31.81 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 36.4 GB | 46.5 GB | 35.44 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 44.6 GB | 54.7 GB | 43.62 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 52.8 GB | 62.8 GB | 51.80 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q8_0 | 8.00 | 73.7 GB | 83.7 GB | 72.71 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Qwen2 72B Instruct FP8?
Q4_K_M · 44.6 GBQwen2 72B Instruct FP8 (Q4_K_M) requires 44.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 58+ GB is recommended. Using the full 33K context window can add up to 10.1 GB, bringing total usage to 54.7 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Qwen2 72B Instruct FP8?
Q4_K_M · 44.6 GB11 devices with unified memory can run Qwen2 72B Instruct FP8, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Related Models
Frequently Asked Questions
- How much VRAM does Qwen2 72B Instruct FP8 need?
Qwen2 72B Instruct FP8 requires 44.6 GB of VRAM at Q4_K_M, or 73.7 GB at Q8_0. Full 33K context adds up to 10.1 GB (54.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 72.7B × 4.8 bits ÷ 8 = 43.6 GB
KV Cache + Overhead ≈ 1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 11.1 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M44.6 GBQ4_K_M + full context54.7 GB- Can NVIDIA GeForce RTX 4090 run Qwen2 72B Instruct FP8?
Yes, at IQ2_XXS (21.0 GB) or lower. Higher quantizations like IQ2_M (25.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Qwen2 72B Instruct FP8?
For Qwen2 72B Instruct FP8, Q4_K_M (44.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (52.8 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 21.0 GB.
VRAM requirement by quantization
IQ2_XXS21.0 GBQ2_K31.9 GBIQ3_M33.7 GBQ4_K_M ★44.6 GBQ5_K_M52.8 GBQ8_073.7 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwen2 72B Instruct FP8 on a Mac?
Qwen2 72B Instruct FP8 requires at least 21.0 GB at IQ2_XXS, 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 Qwen2 72B Instruct FP8 locally?
Yes — Qwen2 72B Instruct FP8 can run locally on consumer hardware. At Q4_K_M quantization it needs 44.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen2 72B Instruct FP8?
At Q4_K_M, Qwen2 72B Instruct FP8 can reach ~65 tok/s on AMD Instinct MI300X. 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 ÷ 44.6 × 0.55 = ~65 tok/s
Estimated speed at Q4_K_M (44.6 GB)
~65 tok/s~49 tok/s~40 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwen2 72B Instruct FP8?
At Q4_K_M, the download is about 43.62 GB. The full-precision Q8_0 version is 72.71 GB. The smallest option (IQ2_XXS) is 19.99 GB.
- Which GPUs can run Qwen2 72B Instruct FP8?
No single consumer GPU has enough VRAM to run Qwen2 72B Instruct FP8 at Q4_K_M (44.6 GB). Multi-GPU or professional hardware is required.
- Which devices can run Qwen2 72B Instruct FP8?
11 devices with unified memory can run Qwen2 72B Instruct FP8 at Q4_K_M (44.6 GB), including Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.