Views
No views yet
llama-cli -hf liodon-ai/Hermes-3-Llama-3.1-8B-imatrix-GGUF:Q4_K_Mollama run hf.co/liodon-ai/Hermes-3-Llama-3.1-8B-imatrix-GGUF:Q4_K_Mliodon-ai/Hermes-3-Llama-3.1-8B-imatrix-GGUF and pick your quant.| Quant | Size | VRAM est. | Notes |
|---|---|---|---|
IQ2_M | 2.95 GB | ~3 GB | 2-bit, iMatrix — smallest usable |
IQ3_M | 3.78 GB | ~4 GB | 3-bit, iMatrix — great quality/size tradeoff |
IQ4_XS | 4.45 GB | ~5 GB | 4-bit extra-small, iMatrix |
Q4_K_M | 4.92 GB | ~6 GB | 4-bit, iMatrix-calibrated (recommended) |
Q5_K_M | 5.73 GB | ~7 GB | 5-bit, iMatrix-calibrated |
Q6_K | 6.60 GB | ~8 GB | 6-bit, iMatrix-calibrated, near-lossless |
Q8_0 | 8.54 GB | ~10 GB | 8-bit, essentially lossless |
Also see plain (non-iMatrix) quants:liodon-ai/Hermes-3-Llama-3.1-8B-GGUF