Qwen
ReasoningCodingAI codingAI building32.5B
Reasoning

QwQ 32B Preview

Qwen · Apache 2.0

Reasoning-focused model that uses chain-of-thought natively. Builders pair this with a coding model for complex architecture decisions. Approaches o1-mini on reasoning benchmarks. Same size as Qwen 2.5 Coder 32B, so they compete for VRAM; run one at a time, not concurrently.

Parameters
32.5B
Architecture
Dense
Context
131,072 tokens
Released
2024-11-28
Engines
llama.cpp, ollama, vLLM
Builder Tools
Open WebUI, LM Studio

Parameters

32.5B

VRAM

21.9 GB

Context

128K

Formats

5

GPUs

20

QwQ 32B Preview (32.5B) requires 21.9 GB VRAM at recommended quality (Q5_K_M). At efficient quality (Q4_K_M), it fits in 18.4 GB VRAM, making it compatible with the AMD Radeon RX 9060 XT 16GB. On NVIDIA Grace Blackwell Ultra GB300, expect approximately 140 tok/s at Q5_K_M. For the best experience, AMD AI Powerhouse ($1,818) is recommended.

Source: OwnRig methodology

VRAM (Recommended)

21.9 GB

Quantization

Q5_K_M

File Size

19.5 GB

Max Context

128K tokens

Primary Use

Reasoning

Memory

VRAM Requirements

QualityQuantizationVRAMFile Size
fullQ8_034.6 GB32.5 GB
recommendedQ5_K_M21.9 GB19.5 GB
efficientQ4_K_M18.4 GB16.3 GB
compressedQ3_K_M14.8 GB12.7 GB
compressedQ2_K11.6 GB9.8 GB
Scaling

Context Length Impact

KV cache VRAM at Q5_K_M quality. Longer context = more memory.

ContextKV CacheTotal VRAM
2K410 MB22.3 GB
4K819 MB22.7 GB
8K1.5 GB23.4 GB
16K3.1 GB25 GBexceeds 24 GB
32K6.1 GB28 GBexceeds 24 GB
64K12.3 GB34.2 GBexceeds 24 GB
128K24.6 GB46.5 GBexceeds 24 GB

Compatible GPUs

20 devices
NVIDIA Grace Blackwell Ultra GB300Q5_K_M140 tok/sExcellent
Apple M4 Max (128GB Unified)Q8_014 tok/sGood
Apple M4 Max (64GB Unified)Q5_K_M17 tok/sGood
Apple M4 Ultra (192GB)Q8_021 tok/sGood
NVIDIA GeForce RTX 4090Q4_K_M24 tok/sGood
AMD Radeon RX 7900 XTXQ4_K_M21 tok/sGood
AMD Radeon Pro W7900Q5_K_M18 tok/sGood
NVIDIA RTX PRO 6000 BlackwellQ5_K_M50 tok/sGood
NVIDIA RTX PRO 6000 Blackwell Max-QQ5_K_M46 tok/sGood
AMD Radeon RX 9070Q2_KAcceptable
AMD Radeon RX 9060 XT 16GBQ2_KAcceptable
AMD Radeon RX 7600Q2_K2 tok/sMarginal
Apple M3 Pro (18GB Unified)Q3_K_MNot viable
NVIDIA GeForce RTX 3080 10GBQ2_KNot viable
NVIDIA GeForce RTX 4060 8GBQ2_KNot viable
NVIDIA RTX 4060 Laptop (40-60W)Q2_KNot viable
NVIDIA RTX 4070 Laptop (80-115W)Q2_KNot viable
NVIDIA GeForce RTX 4070 Ti 12GBQ2_KNot viable
AMD Radeon RX 9060 XT 8GBQ2_KNot viable
NVIDIA GeForce RTX 5060 8GBQ2_KNot viable

Showing 20 of 20 entries

Builder Context

QwQ 32B Preview is commonly used with Open WebUI, LM Studio. For an AI coding workflow, pair it with an embedding model like nomic-embed-text for local RAG.

Hardware

Recommended Builds

Complete PC builds that can run QwQ 32B Preview.

FAQ

Frequently Asked Questions

How much VRAM does QwQ 32B Preview need?
QwQ 32B Preview requires 21.9 GB VRAM at recommended quality (Q5_K_M). At lower quality settings, it can fit in as little as 11.6 GB.
What is the best GPU for QwQ 32B Preview?
The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for QwQ 32B Preview, achieving 140 tok/s at Q5_K_M with an excellent rating.
What quantization should I use for QwQ 32B Preview?
For the best quality, use Q5_K_M (21.9 GB VRAM). If your GPU has limited VRAM, Q2_K (11.6 GB) is the most efficient option with acceptable quality.
Is QwQ 32B Preview good for coding?
Yes. QwQ 32B Preview is used with Open WebUI, LM Studio for local AI coding. For the best coding experience, pair it with an embedding model for local RAG.
All models

Data confidence: estimated. Source

VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.Qwen is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.