metadata

base_model: Qwen/QwQ-32B
language:
  - en
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/QWQ-32B/blob/main/LICENSE
pipeline_tag: text-generation
tags:
  - chat
  - llama-cpp
  - gguf-my-repo

Triangle104/QwQ-32B-Q8_0-GGUF

This model was converted to GGUF format from Qwen/QwQ-32B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

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.

This repo contains the QwQ 32B model, which has the following features:

-Type: Causal Language Models

-Training Stage: Pretraining & Post-training (Supervised Finetuning and Reinforcement Learning)

-Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias

-Number of Parameters: 32.5B

-Number of Paramaters (Non-Embedding): 31.0B

-Number of Layers: 64

-Number of Attention Heads (GQA): 40 for Q and 8 for KV

-Context Length: Full 131,072 tokens

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Triangle104/QwQ-32B-Q8_0-GGUF --hf-file qwq-32b-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/QwQ-32B-Q8_0-GGUF --hf-file qwq-32b-q8_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Triangle104/QwQ-32B-Q8_0-GGUF --hf-file qwq-32b-q8_0.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo Triangle104/QwQ-32B-Q8_0-GGUF --hf-file qwq-32b-q8_0.gguf -c 2048