Qwen/Qwen2.5-32B-Instruct
Full fine-tune vs Qwen/Qwen2.5-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 128/129, MLP 192/192, Attention 448/448, lm_head 1/1
128 derivatives checked
- Qwen/Qwen2.5-32B-Instruct-AWQ: Quantization
- bartowski/Qwen2.5-32B-Instruct-GGUF: Same weights, converted
- Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4: Quantization
- unsloth/Qwen2.5-32B-Instruct-bnb-4bit: Quantization
- Qwen/QwQ-32B-Preview: Full fine-tune
- Qwen/Qwen2.5-32B-Instruct-GGUF: Full fine-tune
- huihui-ai/Qwen2.5-32B-Instruct-abliterated: Abliterated
- Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8: Quantization
- lmstudio-community/Qwen2.5-32B-Instruct-GGUF: Quantization
- zetasepic/Qwen2.5-32B-Instruct-abliterated-v2-GGUF: Full fine-tune
- ThomasBaruzier/QwQ-32B-Preview-GGUF: Full fine-tune
- EasierAI/Qwen-2.5-32B: Quantization
- TheRains/Qwen2.5-32B-Instruct-Q4_K_M-GGUF: Quantization
- MaziyarPanahi/Qwen2.5-32B-Instruct-GGUF: Quantization
- unsloth/Qwen2.5-32B-Instruct: Same weights, repacked
- Mungert/OpenCodeReasoning-Nemotron-32B-IOI-GGUF: Full fine-tune
- lmstudio-community/Qwen2.5-32B-Instruct-MLX-4bit: Quantization
- Mungert/OpenReasoning-Nemotron-32B-GGUF: Full fine-tune
- legraphista/Qwen2.5-32B-Instruct-IMat-GGUF: Same weights, converted
- pbhappliedsystems/qwen-2.5-32B-instruct-gguf-Q4-K-M: Quantization
- drawais/Qwen2.5-32B-Instruct-AWQ-INT4: Quantization
- Mungert/OpenCodeReasoning-Nemotron-32B-GGUF: Full fine-tune
- second-state/Qwen2.5-32B-Instruct-GGUF: Same weights, converted
- sugoitoolkit/Sugoi-32B-Ultra-GGUF: LoRA-style
- lmstudio-community/Qwen2.5-32B-Instruct-MLX-8bit: Quantization
- gaianet/Qwen2.5-32B-Instruct-GGUF: Same weights, converted
- quantized4all/OpenCodeReasoning-Nemotron-1.1-32B-GGUF: Full fine-tune
- featherless-ai-quants/Qwen-Qwen2.5-32B-Instruct-GGUF: Quantization
- mradermacher/Qwen2.5-32B-Instruct-i1-GGUF: Quantization
- BCCard/Qwen2.5-Coder-32B-Instruct-FP8-Dynamic: Quantization
14 other repos hold byte-for-byte identical weight files.