QwQ 32B Preview GGUF — Hardware Requirements & GPU Compatibility
ChatReasoning
32 downloads
16 likesSpecifications
- Publisher
- LM Studio Community
- Family
- QwQ
- Parameters
- 32B
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does QwQ 32B Preview GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q3_K_L | 4.10 | 18.0 GB | — | 16.40 GB | 3-bit large quantization |
| Q4_K_M | 4.80 | 21.1 GB | — | 19.20 GB | 4-bit medium quantization — most popular sweet spot |
| Q6_K | 6.60 | 29.0 GB | — | 26.40 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 35.2 GB | — | 32.00 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run QwQ 32B Preview GGUF?
Q4_K_M · 21.1 GBQwQ 32B Preview GGUF (Q4_K_M) requires 21.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 28+ GB is recommended. 5 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run QwQ 32B Preview GGUF?
Q4_K_M · 21.1 GB21 devices with unified memory can run QwQ 32B Preview GGUF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does QwQ 32B Preview GGUF need?
QwQ 32B Preview GGUF requires 21.1 GB of VRAM at Q4_K_M, or 35.2 GB at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 32B × 4.8 bits ÷ 8 = 19.2 GB
KV Cache + Overhead ≈ 1.9 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M21.1 GB- Can NVIDIA GeForce RTX 4090 run QwQ 32B Preview GGUF?
Yes, at Q4_K_M (21.1 GB) or lower. Higher quantizations like Q6_K (29.0 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for QwQ 32B Preview GGUF?
For QwQ 32B Preview GGUF, Q4_K_M (21.1 GB) offers the best balance of quality and VRAM usage. Q6_K (29.0 GB) provides better quality if you have the VRAM. The smallest option is Q3_K_L at 18.0 GB.
VRAM requirement by quantization
Q3_K_L18.0 GB~86%Q4_K_M ★21.1 GB~89%Q6_K29.0 GB~95%Q8_035.2 GB~99%★ Recommended — best balance of quality and VRAM usage.
- Can I run QwQ 32B Preview GGUF on a Mac?
QwQ 32B Preview GGUF requires at least 18.0 GB at Q3_K_L, 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 QwQ 32B Preview GGUF locally?
Yes — QwQ 32B Preview GGUF can run locally on consumer hardware. At Q4_K_M quantization it needs 21.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is QwQ 32B Preview GGUF?
At Q4_K_M, QwQ 32B Preview GGUF can reach ~138 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~31 tok/s. 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 ÷ 21.1 × 0.55 = ~138 tok/s
Estimated speed at Q4_K_M (21.1 GB)
AMD Instinct MI300X~138 tok/sNVIDIA GeForce RTX 4090~31 tok/sNVIDIA H100 SXM~103 tok/sAMD Instinct MI250X~85 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of QwQ 32B Preview GGUF?
At Q4_K_M, the download is about 19.20 GB. The full-precision Q8_0 version is 32.00 GB. The smallest option (Q3_K_L) is 16.40 GB.
- Which GPUs can run QwQ 32B Preview GGUF?
5 consumer GPUs can run QwQ 32B Preview GGUF at Q4_K_M (21.1 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 QwQ 32B Preview GGUF?
21 devices with unified memory can run QwQ 32B Preview GGUF at Q4_K_M (21.1 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.