QwQ-32B#

  • Context Length: 32768

  • Model Name: QwQ-32B

  • Languages: en, zh

  • Abilities: chat, reasoning

  • Description: QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.

Specifications#

Model Spec 1 (pytorch, 32 Billion)#

  • Model Format: pytorch

  • Model Size (in billions): 32

  • Quantizations: 4-bit, 8-bit, none

  • Engines: vLLM, Transformers, SGLang (vLLM and SGLang only available for quantization none)

  • Model ID: Qwen/QwQ-32B

  • Model Hubs: Hugging Face, ModelScope

Execute the following command to launch the model, remember to replace ${quantization} with your chosen quantization method from the options listed above:

xinference launch --model-engine ${engine} --model-name QwQ-32B --size-in-billions 32 --model-format pytorch --quantization ${quantization}

Model Spec 2 (awq, 32 Billion)#

  • Model Format: awq

  • Model Size (in billions): 32

  • Quantizations: Int4

  • Engines: vLLM, Transformers, SGLang

  • Model ID: Qwen/QwQ-32B-AWQ

  • Model Hubs: Hugging Face, ModelScope

Execute the following command to launch the model, remember to replace ${quantization} with your chosen quantization method from the options listed above:

xinference launch --model-engine ${engine} --model-name QwQ-32B --size-in-billions 32 --model-format awq --quantization ${quantization}

Model Spec 3 (mlx, 32 Billion)#

  • Model Format: mlx

  • Model Size (in billions): 32

  • Quantizations: 3bit, 4bit, 6bit, 8bit, bf16

  • Engines: MLX

  • Model ID: mlx-community/QwQ-32B-{quantization}

  • Model Hubs: Hugging Face, ModelScope

Execute the following command to launch the model, remember to replace ${quantization} with your chosen quantization method from the options listed above:

xinference launch --model-engine ${engine} --model-name QwQ-32B --size-in-billions 32 --model-format mlx --quantization ${quantization}

Model Spec 4 (ggufv2, 32 Billion)#

  • Model Format: ggufv2

  • Model Size (in billions): 32

  • Quantizations: fp16, Q2_k, Q3_K_M, Q4_0, Q4_K_M, Q5_0, Q5_K_M, Q6_K, Q8_0

  • Engines: llama.cpp

  • Model ID: Qwen/QwQ-32B-GGUF

  • Model Hubs: Hugging Face, ModelScope

Execute the following command to launch the model, remember to replace ${quantization} with your chosen quantization method from the options listed above:

xinference launch --model-engine ${engine} --model-name QwQ-32B --size-in-billions 32 --model-format ggufv2 --quantization ${quantization}