XiYanSQL QwenCoder 32B 2504 — Hardware Requirements & GPU Compatibility
ChatCode
XiYanSQL QwenCoder 32B 2504 is a 32B-parameter open language model from XGenerationLab in the Qwen family. It supports a context window of up to 32,768 tokens. At BF16 it needs about 64.84 GB of VRAM — see which GPUs and Macs can run it below.
127 downloads
19 likesSpecifications
- Publisher
- XGenerationLab
- Family
- Qwen
- Parameters
- 32B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2025-12-04
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does XiYanSQL QwenCoder 32B 2504 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 64.8 GB | 72.9 GB | 64.00 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run XiYanSQL QwenCoder 32B 2504?
BF16 · 64.8 GBXiYanSQL QwenCoder 32B 2504 (BF16) requires 64.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 85+ GB is recommended. Using the full 33K context window can add up to 8.0 GB, bringing total usage to 72.9 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run XiYanSQL QwenCoder 32B 2504?
BF16 · 64.8 GB5 devices with unified memory can run XiYanSQL QwenCoder 32B 2504, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Related Models
Frequently Asked Questions
- How much VRAM does XiYanSQL QwenCoder 32B 2504 need?
XiYanSQL QwenCoder 32B 2504 requires 64.8 GB of VRAM at BF16. Full 33K context adds up to 8.0 GB (72.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32B × 16 bits ÷ 8 = 64 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
BF1664.8 GBBF16 + full context72.9 GB- Can NVIDIA GeForce RTX 5090 run XiYanSQL QwenCoder 32B 2504?
No — XiYanSQL QwenCoder 32B 2504 requires at least 64.8 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run XiYanSQL QwenCoder 32B 2504 on a Mac?
XiYanSQL QwenCoder 32B 2504 requires at least 64.8 GB at BF16, 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 XiYanSQL QwenCoder 32B 2504 locally?
Yes — XiYanSQL QwenCoder 32B 2504 can run locally on consumer hardware. At BF16 quantization it needs 64.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is XiYanSQL QwenCoder 32B 2504?
At BF16, XiYanSQL QwenCoder 32B 2504 can reach ~45 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 ÷ 64.8 × 0.55 = ~45 tok/s
Estimated speed at BF16 (64.8 GB)
~45 tok/s~34 tok/s~28 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of XiYanSQL QwenCoder 32B 2504?
At BF16, the download is about 64.00 GB.
- Which GPUs can run XiYanSQL QwenCoder 32B 2504?
No single consumer GPU has enough VRAM to run XiYanSQL QwenCoder 32B 2504 at BF16 (64.8 GB). Multi-GPU or professional hardware is required.
- Which devices can run XiYanSQL QwenCoder 32B 2504?
5 devices with unified memory can run XiYanSQL QwenCoder 32B 2504 at BF16 (64.8 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB), NVIDIA DGX A100 640GB. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.