Qwen1.5 32B Chat — Hardware Requirements & GPU Compatibility
Chat
Qwen1.5-32B-Chat is Alibaba's instruction-tuned, 32.5-billion-parameter chat model from the Qwen1.5 series, a beta release of the Qwen2 architecture that sits between the 14B and 72B dense models in the lineup. Qwen1.5 improved on the original Qwen with stable 32K context support across all model sizes, broader multilingual coverage, and no need for custom trust_remote_code, and this 32B checkpoint additionally uses grouped-query attention, unlike the smaller Qwen1.5 sizes, for faster inference. It was aligned on top of the pretrained base with supervised fine-tuning and direct preference optimization. At 32.5 billion parameters it needs a high-end consumer GPU, or a multi-GPU setup once quantized, to run comfortably. Context length is 32,768 tokens. It is released under Alibaba's Tongyi Qianwen license, a custom license that is free for most commercial and research use but requires a separate license from Alibaba once a deployment exceeds 100 million monthly active users. It was published in April 2024, part of Alibaba's second LLM generation, later followed by Qwen2 and Qwen2.5.
44.4K downloads
108 likesSpecifications
- Publisher
- Alibaba
- Family
- Qwen
- Parameters
- 32.5B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2024-04-03
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Qwen1.5 32B Chat Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 14.7 GB | 22.7 GB | 13.82 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 15.1 GB | 23.1 GB | 14.22 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 16.7 GB | 24.7 GB | 15.85 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 20.3 GB | 28.4 GB | 19.51 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 24 GB | 32.0 GB | 23.16 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 27.7 GB | 35.7 GB | 26.82 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 33.4 GB | 41.4 GB | 32.51 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 32B Chat?
Q4_K_M · 20.3 GBQwen1.5 32B Chat (Q4_K_M) requires 20.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 27+ GB is recommended. Using the full 33K context window can add up to 8.1 GB, bringing total usage to 28.4 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Qwen1.5 32B Chat?
Q4_K_M · 20.3 GB41 devices with unified memory can run Qwen1.5 32B Chat, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Qwen1.5 32B 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 32B Chat need?
Qwen1.5 32B Chat requires 20.3 GB of VRAM at Q4_K_M, or 65.9 GB at BF16. Full 33K context adds up to 8.1 GB (28.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32.5B × 4.8 bits ÷ 8 = 19.5 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 8.9 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M20.3 GBQ4_K_M + full context28.4 GB- Can NVIDIA GeForce RTX 4090 run Qwen1.5 32B Chat?
Yes, at Q5_K_M (24 GB) or lower. Higher quantizations like Q6_K (27.7 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Qwen1.5 32B Chat?
For Qwen1.5 32B Chat, Q4_K_M (20.3 GB) offers the best balance of quality and VRAM usage. Q5_K_S (23.2 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XS at 14.3 GB.
VRAM requirement by quantization
IQ3_XS14.3 GBIQ3_M15.5 GBIQ4_XS18.3 GBQ4_K_M ★20.3 GBQ5_K_M24.0 GBBF1665.9 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwen1.5 32B Chat on a Mac?
Qwen1.5 32B Chat requires at least 14.3 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 32B Chat locally?
Yes — Qwen1.5 32B Chat can run locally on consumer hardware. At Q4_K_M quantization it needs 20.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen1.5 32B Chat?
At Q4_K_M, Qwen1.5 32B Chat can reach ~236 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~32 tok/s. 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 ÷ 20.3 × 0.65 = ~256 tok/s
Estimated speed at Q4_K_M (20.3 GB)
~256 tok/s~32 tok/s~256 tok/s~236 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 32B Chat?
At Q4_K_M, the download is about 19.51 GB. The full-precision BF16 version is 65.02 GB. The smallest option (IQ3_XS) is 13.41 GB.
- Which GPUs can run Qwen1.5 32B Chat?
7 consumer GPUs can run Qwen1.5 32B Chat at Q4_K_M (20.3 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Qwen1.5 32B Chat?
41 devices with unified memory can run Qwen1.5 32B Chat at Q4_K_M (20.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.