NousResearch/Hermes-3-Llama-3.1-8B
Full fine-tune vs meta-llama/Llama-3.1-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 64/65, MLP 96/96, Attention 128/128, lm_head 1/1
52 derivatives checked
- solidrust/Hermes-3-Llama-3.1-8B-AWQ: Quantization
- bartowski/Hermes-3-Llama-3.1-8B-GGUF: Quantization
- unsloth/Hermes-3-Llama-3.1-8B-bnb-4bit: Quantization
- legraphista/Hermes-3-Llama-3.1-8B-IMat-GGUF: Same weights, converted
- mradermacher/Hermes-3-Llama-3.1-8B-i1-GGUF: Quantization
- QuantFactory/Hermes-3-Llama-3.1-8B-lorablated-GGUF: Full fine-tune
- mradermacher/Hermes-3-Llama-3.1-8B-GGUF: Same weights, converted
- backyardai/Hermes-3-Llama-3.1-8B-GGUF: Quantization
- QuantFactory/Hermes-3-Llama-3.1-8B-Kor-Finance-Advisor-GGUF: Quantization
- tda45/TdAI: Identical copy
- featherless-ai-quants/NousResearch-Hermes-3-Llama-3.1-8B-GGUF: Quantization
- Saxo/Linkbricks-Horizon-AI-Korean-Advanced-8B: LoRA-style
- itlwas/Hermes-3-Llama-3.1-8B-Q4_K_M-GGUF: Quantization
- squ11z1/Hypnos-i1-8B: Full fine-tune
- liodon-ai/Hermes-3-Llama-3.1-8B-imatrix-GGUF: Quantization
- Yingyaeliae/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF-heretic: Full fine-tune
- QuantFactory/Albatross2.1-8B-Instruct-GGUF: Full fine-tune
- ClaudioItaly/Hermes-3-Llama-3.1-8B-Q5_K_M-GGUF: Quantization
- mlx-community/Hermes-3-Llama-3.1-8B-MLX: Same weights, converted
- solanaclawd/solana-nvidia-trading-factory-8b: LoRA-style
- lowlevelgoblin/Hermes-3-Llama-3.1-8B-Q4_K_M-GGUF: Quantization
- mlabonne/Hermes-3-Llama-3.1-8B-lorablated: Full fine-tune
- LoganResearch/Nous-Hermes-ReflexAgent-8B-v1: LoRA-style
- mookiezii/Discord-Hermes-3-8B: LoRA-style
- LoganResearch/ARC-Base-8B-Condensed: LoRA-style
- vicgalle/Configurable-Hermes-3-Llama-3.1-8B: LoRA-style
- Etherll/Herplete-LLM-Llama-3.1-8b: Full fine-tune
- ehristoforu/mllama-3.1-8b-instruct: Full fine-tune
- agentlans/Llama3.1-LexiHermes-SuperStorm: Full fine-tune
- Yingyaeliae/Hypnos-i1-8B-heretic: Full fine-tune
22 other repos hold byte-for-byte identical weight files.