Qwen1.5 72B Chat — Hardware Requirements & GPU Compatibility
Chat
Qwen1.5 72B Chat is a 72.3B-parameter open language model from Alibaba in the Qwen family. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 49.04 GB of VRAM — see which GPUs and Macs can run it below.
10.1K downloads
217 likesSpecifications
- Publisher
- Alibaba
- Family
- Qwen
- Parameters
- 72.3B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 152,064
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Qwen1.5 72B Chat Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 36.4 GB | 116.9 GB | 30.72 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 37.3 GB | 117.8 GB | 31.63 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 40.9 GB | 121.4 GB | 35.24 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 49.0 GB | 129.6 GB | 43.37 GB | 4-bit medium quantization — most popular sweet spot |
Which GPUs Can Run Qwen1.5 72B Chat?
Q4_K_M · 49.0 GBQwen1.5 72B Chat (Q4_K_M) requires 49.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 64+ GB is recommended. Using the full 33K context window can add up to 80.5 GB, bringing total usage to 129.6 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Qwen1.5 72B Chat?
Q4_K_M · 49.0 GB8 devices with unified memory can run Qwen1.5 72B Chat, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightBenchmarks
View all 1 →Related Models
Derivatives (1)
Frequently Asked Questions
- How much VRAM does Qwen1.5 72B Chat need?
Qwen1.5 72B Chat requires 49.0 GB of VRAM at Q4_K_M, or 55.4 GB at Q5_K_S. Full 33K context adds up to 80.5 GB (129.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 72.3B × 4.8 bits ÷ 8 = 43.4 GB
KV Cache + Overhead ≈ 5.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 86.2 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M49.0 GBQ4_K_M + full context129.6 GB- Can NVIDIA GeForce RTX 5090 run Qwen1.5 72B Chat?
No — Qwen1.5 72B Chat requires at least 35.5 GB at IQ3_XS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for Qwen1.5 72B Chat?
For Qwen1.5 72B Chat, Q4_K_M (49.0 GB) offers the best balance of quality and VRAM usage. Q5_K_S (55.4 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XS at 35.5 GB.
VRAM requirement by quantization
IQ3_XS35.5 GBQ3_K_S37.3 GBQ3_K_M40.9 GBQ4_K_S46.3 GBQ4_K_M ★49.0 GBQ5_K_S55.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwen1.5 72B Chat on a Mac?
Qwen1.5 72B Chat requires at least 35.5 GB at IQ3_XS, 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 Qwen1.5 72B Chat locally?
Yes — Qwen1.5 72B Chat can run locally on consumer hardware. At Q4_K_M quantization it needs 49.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen1.5 72B Chat?
At Q4_K_M, Qwen1.5 72B Chat can reach ~59 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 ÷ 49.0 × 0.55 = ~59 tok/s
Estimated speed at Q4_K_M (49.0 GB)
~59 tok/s~44 tok/s~37 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwen1.5 72B Chat?
At Q4_K_M, the download is about 43.37 GB. The full-precision Q5_K_S version is 49.70 GB. The smallest option (IQ3_XS) is 29.82 GB.
- Which GPUs can run Qwen1.5 72B Chat?
No single consumer GPU has enough VRAM to run Qwen1.5 72B Chat at Q4_K_M (49.0 GB). Multi-GPU or professional hardware is required.
- Which devices can run Qwen1.5 72B Chat?
8 devices with unified memory can run Qwen1.5 72B Chat at Q4_K_M (49.0 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB), Mac Studio M4 Max (64 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.