Qwen/Qwen2.5-14B-Instruct
Full fine-tune vs Qwen/Qwen2.5-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336, lm_head 1/1
169 derivatives checked
- Qwen/Qwen2.5-14B-Instruct-AWQ: Quantization
- Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4: Quantization
- bartowski/Qwen2.5-14B-Instruct-GGUF: Same weights, converted
- Qwen/Qwen2.5-14B-Instruct-GGUF: Partial fine-tune
- unsloth/Qwen2.5-14B-Instruct: Same weights, repacked
- unsloth/Qwen2.5-14B-Instruct-bnb-4bit: Quantization
- lmstudio-community/Qwen2.5-14B-Instruct-GGUF: Quantization
- unsloth/Qwen2.5-14B-Instruct-unsloth-bnb-4bit: Quantization
- lmstudio-community/Qwen2.5-14B-Instruct-MLX-4bit: Quantization
- mradermacher/Qwen2.5-14B-Instruct-i1-GGUF: Quantization
- mradermacher/Qwen2.5-14B-Instruct-GGUF: Quantization
- legraphista/Qwen2.5-14B-Instruct-IMat-GGUF: Same weights, converted
- TheRains/Qwen2.5-14B-Instruct-Q4_K_M-GGUF: Quantization
- Unbabel/M-Prometheus-14B: Full fine-tune
- yimn-Aghosh/zegrate-ai: LoRA-style
- Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8: Quantization
- lmstudio-community/Qwen2.5-14B-Instruct-MLX-8bit: Quantization
- QuantFactory/Qwen2.5-14B-Gutenberg-1e-Delta-GGUF: Quantization
- PollardWeights/Qwen2.5-14B-Instruct-Pollard: Quantization
- Mungert/OpenReasoning-Nemotron-14B-GGUF: Full fine-tune
- QuantFactory/Qwen2.5-14B-Gutenberg-Instruct-Slerpeno-GGUF: Quantization
- QuantFactory/qwen2.5-reinstruct-alternate-lumen-14B-GGUF: Full fine-tune
- MaziyarPanahi/Qwen2.5-14B-Instruct-GGUF: Same weights, converted
- Mungert/OpenCodeReasoning-Nemotron-14B-GGUF: Full fine-tune
- featherless-ai-quants/Qwen-Qwen2.5-14B-Instruct-GGUF: Quantization
- QuantFactory/Replete-LLM-V2.5-Qwen-14b-GGUF: Full fine-tune
- QuantFactory/oxy-1-small-GGUF: Full fine-tune
- saidutta69/Qwen2.5-14B-Instruct-heretic: Abliterated
- QuantFactory/Rombos-LLM-V2.6-Qwen-14b-GGUF: Full fine-tune
- gaianet/Qwen2.5-14B-Instruct-GGUF: Same weights, converted
16 other repos hold byte-for-byte identical weight files.