Qwen/Qwen3-32B
150 derivatives checked
- Qwen/Qwen3-32B-AWQ: Quantization
- RedHatAI/Qwen3-32B-NVFP4: Quantization
- MaziyarPanahi/Qwen3-32B-GGUF: Quantization
- Qwen/Qwen3-32B-FP8: Quantization
- Qwen/Qwen3-32B-GGUF: Quantization
- unsloth/Qwen3-32B-GGUF: Same weights, converted
- unsloth/Qwen3-32B-bnb-4bit: Quantization
- lmstudio-community/Qwen3-32B-MLX-4bit: Quantization
- lmstudio-community/Qwen3-32B-MLX-8bit: Quantization
- nvidia/Qwen3-32B-NVFP4: Quantization
- bartowski/Qwen_Qwen3-32B-GGUF: Same weights, converted
- unsloth/Qwen3-32B-unsloth-bnb-4bit: Quantization
- unsloth/Qwen3-32B: Same weights, repacked
- Goedel-LM/Goedel-Prover-V2-32B: Full fine-tune
- lmstudio-community/Qwen3-32B-GGUF: Quantization
- RedHatAI/Qwen3-32B-quantized.w4a16: Quantization
- unsloth/Qwen3-32B-128K-GGUF: Same weights, converted
- DavidAU/Qwen3-32B-128k-NEO-Imatrix-Max-GGUF: Quantization
- mlx-community/Qwen3-32B-4bit: Quantization
- johnbridges/UIGEN-X-32B-0727-GGUF: Full fine-tune
- geoffmunn/Qwen3-32B-f16: Not comparable yet
- ecloudtech/Erk-32B: Full fine-tune
- JunHowie/Qwen3-32B-GPTQ-Int4: Quantization
- open-thoughts/OpenThinkerAgent-32B: Full fine-tune
- t-tech/T-pro-it-2.1: Full fine-tune
- ggml-org/Qwen3-32B-GGUF: Same weights, converted
- RefalMachine/RuadaptQwen3-32B-Instruct-GGUF: Quantization
- Trendyol/Trendyol-Cybersecurity-LLM-Qwen3-32B-Q8_0-GGUF: Full fine-tune
- openwalrus/Qwen3-32B: Same weights, converted
- yujiepan/qwen3-tiny-random-tp: Different architecture
27 other repos hold byte-for-byte identical weight files.