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.
9.9K downloads
217 likesSpecifications
- Publisher
- Alibaba
- Family
- Qwen
- Parameters
- 72.3B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2024-01-30
- 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 |
| Q5_K_Mest. | 5.70 | 57.2 GB | 137.7 GB | 51.51 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 65.3 GB | 145.8 GB | 59.64 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 78.0 GB | 158.5 GB | 72.29 GB | 8-bit quantization, near-lossless |
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 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 GB22 devices with unified memory can run Qwen1.5 72B Chat, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 96GB).
Runs great
— Plenty of headroom
Where to Download Qwen1.5 72B Chat
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
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 150.2 GB at BF16. 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 GBIQ3_M38.2 GBIQ4_XS44.5 GBQ4_K_M ★49.0 GBQ5_K_M57.2 GBBF16150.2 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 ~90 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 ÷ 49.0 × 0.65 = ~106 tok/s
Estimated speed at Q4_K_M (49.0 GB)
~106 tok/s~106 tok/s~90 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 BF16 version is 144.58 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?
23 devices with unified memory can run Qwen1.5 72B Chat at Q4_K_M (49.0 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.