family llama · 13 variants · unknown
no scores.
| variant | kind | quant | bits | vRAM | dl | org | year |
|---|---|---|---|---|---|---|---|
| Llama-4-Scout-17B-16E-Instruct-FP8 | fp8 | fp8 | 8.0 | 323,245 | nvidia | 2025 | |
| Llama-4-Scout-17B-16E-Instruct-NVFP4 | nvfp4 | nvfp4 | 4.0 | 72,603 | nvidia | 2025 | |
| Llama-4-Scout-17B-16E-Instruct-GGUF | gguf | gguf | 16.0 | 32,292 | unsloth | 2025 | |
| Llama-4-Scout-17B-16E-Instruct | original | bf16 | 16.0 | 4,930 | unsloth | 2025 | |
| Llama-4-Scout-17B-16E-MLX-text-8bit | mlx | mlx | 2,444 | lmstudio-community | 2025 | ||
| Llama-4-Scout-17B-16E-Instruct-GGUF | gguf | gguf | 3.0 | 1,667 | lmstudio-community | 2025 | |
| meta-llama_Llama-4-Scout-17B-16E-Instruct-old-GGUF | gguf | gguf | 1.0 | 1,609 | bartowski | 2025 | |
| Llama-4-Scout-17B-16E-Instruct-GGUF | gguf | gguf | 4.0 | 1,565 | mradermacher | 2025 | |
| Llama-4-Scout-17B-16E-MLX-text-4bit | mlx | mlx | 1,072 | lmstudio-community | 2025 | ||
| Llama-4-Scout-17B-16E-Instruct-GGUF | gguf | gguf | 4.0 | 315 | ggml-org | 2025 | |
| Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit | bnb-4bit | 4bit | 206 | unsloth | 2025 | ||
| Llama-4-Scout-17B-16E | original | bf16 | 16.0 | 108 | unsloth | 2025 | |
| Llama-4-Scout-17B-16E-Instruct-unsloth-dynamic-bnb-4bit | bnb-4bit | 4bit | 81 | unsloth | 2025 |