family llama · 11 variants · unknown
no scores.
| variant | kind | quant | bits | vRAM | dl | org | year |
|---|---|---|---|---|---|---|---|
| Llama-3.1-8B-Instruct | original | bf16 | 16.0 | 7,952,157 | meta-llama | 2024 | |
| Meta-Llama-3.1-8B-Instruct-AWQ-INT4 | awq | awq | 188,386 | hugging-quants | 2024 | ||
| Llama-Guard-3-8B | original | bf16 | 16.0 | 127,894 | meta-llama | 2024 | |
| Meta-Llama-3.1-8B | original | bf16 | 16.0 | 29,443 | unsloth | 2025 | |
| Meta-Llama-3.1-8B-bnb-4bit | bnb-4bit | 4bit | 23,769 | unsloth | 2025 | ||
| Meta-Llama-3.1-8B-Instruct-GPTQ-INT4 | gptq | gptq | 9,264 | hugging-quants | 2024 | ||
| Llama-3.1-8B-Instruct-GGUF | gguf | gguf | 16.0 | 392 | Mungert | 2025 | |
| Llama-Guard-3-8B-GGUF | gguf | gguf | 16.0 | 339 | Mungert | 2025 | |
| DeepHermes-3-Llama-3-8B-Preview-GGUF | gguf | gguf | 16.0 | 130 | Mungert | 2025 | |
| TwinLlama-3.1-8B | original | bf16 | 16.0 | 84 | mlabonne | 2024 | |
| TwinLlama-3.1-8B-GGUF | gguf | gguf | 8.0 | 70 | mlabonne | 2024 |