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 Q4_K_M it needs about 20.04 GB of VRAM — see which GPUs and Macs can run it below.
Usable on a 24 GB GPU
Runs on 24 GB (Q4_K_M · ~33 tok/s · 16K)Macs from 24 GB (Q4_K_M · ~11 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run XiYanSQL QwenCoder 32B 2504
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve XGenerationLab/XiYanSQL-QwenCoder-32B-2504 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX PRO 4500 (32 GB) (8 GB headroom) · Q4_K_M
- Generation speed
- ~29 tok/s
- generation speed
- Cost per 1M output tokens
- $3.25
- per 1M output tokens
How Much VRAM Does XiYanSQL QwenCoder 32B 2504 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 14.4 GB | 22.5 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~45 tok/s | |
| 16.4 GB | 24.5 GB | 3-bit medium — 3-bit medium quantization | Fits: 16K context · ~40 tok/s | |
| 20.0 GB | 28.1 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 16K context · ~33 tok/s | |
| 23.6 GB | 31.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 2K context · ~28 tok/s | |
| 27.2 GB | 35.3 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 31 GB | |
| 32.8 GB | 40.9 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 36.6 GB | |
| 64.8 GB | 72.9 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 68.6 GB |
Selected Q4_K_M
4-bit medium quantization23.8GBat 16K context
- Weights
- 19.2 GB
- KV cache
- 4.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 0.2 GB free · ~33 tok/s
≥50 tok/s needs ≥1.54 TB/s · RTX 5090 ~58
Which Hardware Can Run XiYanSQL QwenCoder 32B 2504?
Q4_K_M · 20.0 GBXiYanSQL QwenCoder 32B 2504 (Q4_K_M) requires 20.0 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 28.1 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run XiYanSQL QwenCoder 32B 2504, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit Q2_K (18.2 GB)
1 GPU
RX 7900 XT~33Simulate output on RX 7900 XT32–40 GB
fits · 8.2 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~58Simulate output on RTX 5090M5 Max36 GB~16Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to XiYanSQL QwenCoder 32B 2504
Qwen family · 28 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Hy Memory 30B A3BTencent | — | 19.1 GB | ~184 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Llm Jp 4.1 33B Thinkingllm-jp | — | 22.5 GB | ~35 | same size |
| Agnes 3.0 FlashAgnes-AI | — | 22.1 GB | ~35 | same size |
| Muse Glimmer 30BMeta | — | 19.6 GB | ~36 | same size |
| NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA | — | 19.3 GB | ~197 | same size |
Specifications
- Publisher
- XGenerationLab
- Family
- Qwen
- Parameters
- 32B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2025-04-27
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does XiYanSQL QwenCoder 32B 2504 need?
XiYanSQL QwenCoder 32B 2504 requires 20.0 GB of VRAM at Q4_K_M, or 64.8 GB at BF16. Full 33K context adds up to 8.1 GB (28.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32B × 4.8 bits ÷ 8 = 19.2 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 8.9 GB (at full 33K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run XiYanSQL QwenCoder 32B 2504?
Yes, at Q5_K_M (23.6 GB) or lower. Higher quantizations like Q6_K (27.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for XiYanSQL QwenCoder 32B 2504?
For XiYanSQL QwenCoder 32B 2504, Q4_K_M (20.0 GB) offers the best balance of quality and VRAM usage. Q5_K_M (23.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 14.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run XiYanSQL QwenCoder 32B 2504 on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run XiYanSQL QwenCoder 32B 2504. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 20.0 GB of usable unified memory (RAM minus macOS overhead).
Can I run XiYanSQL QwenCoder 32B 2504 locally?
Yes — XiYanSQL QwenCoder 32B 2504 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is XiYanSQL QwenCoder 32B 2504?
At Q4_K_M, XiYanSQL QwenCoder 32B 2504 can reach ~240 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~33 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 ÷ 20.0 × 0.65 = ~260 tok/s
Estimated speed at Q4_K_M (20.0 GB)
Real-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 Q4_K_M, the download is about 19.20 GB. The full-precision BF16 version is 64.00 GB. The smallest option (Q2_K) is 13.60 GB.
Which GPUs can run XiYanSQL QwenCoder 32B 2504?
7 consumer GPUs can run XiYanSQL QwenCoder 32B 2504 at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run XiYanSQL QwenCoder 32B 2504?
122 devices with unified memory can run XiYanSQL QwenCoder 32B 2504 at Q4_K_M (20.0 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, 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.