family qwen · 15 variants · unknown
no scores.
| variant | kind | quant | bits | vRAM | dl | org | year |
|---|---|---|---|---|---|---|---|
| Qwen3-VL-32B-Instruct | original | bf16 | 16.0 | 2,929,552 | Qwen | 2025 | |
| Qwen3-VL-32B-Instruct-FP8 | fp8 | fp8 | 8.0 | 761,656 | Qwen | 2025 | |
| Qwen3-VL-32B-Instruct-bnb-4bit | bnb-4bit | 4bit | 541,501 | unsloth | 2025 | ||
| Qwen3-VL-32B-Instruct-GGUF | gguf | gguf | 16.0 | 13,398 | Qwen | 2025 | |
| Qwen3-VL-32B-Instruct-GGUF | gguf | gguf | 16.0 | 10,613 | unsloth | 2026 | |
| Qwen_Qwen3-VL-32B-Instruct-GGUF | gguf | gguf | 2.0 | 5,952 | bartowski | 2025 | |
| Qwen3-VL-32B-Instruct-GGUF | gguf | gguf | 4.0 | 5,452 | lmstudio-community | 2025 | |
| Cosmos-Reason2-32B | original | bf16 | 16.0 | 3,686 | nvidia | 2026 | |
| Qwen3-VL-32B-Instruct-unsloth-bnb-4bit | bnb-4bit | 4bit | 1,793 | unsloth | 2025 | ||
| Qwen3-VL-32B-Instruct-MLX-6bit | mlx | mlx | 1,588 | lmstudio-community | 2025 | ||
| Qwen3-VL-32B-Instruct-1M-GGUF | gguf | gguf | 16.0 | 777 | unsloth | 2025 | |
| Qwen3-VL-32B-Instruct-MLX-4bit | mlx | mlx | 719 | lmstudio-community | 2025 | ||
| Qwen3-VL-32B-Instruct-MLX-8bit | mlx | mlx | 669 | lmstudio-community | 2025 | ||
| Qwen3-VL-32B-Instruct | original | bf16 | 16.0 | 343 | unsloth | 2026 | |
| Qwen3-VL-32B-Instruct-MLX-5bit | mlx | mlx | 330 | lmstudio-community | 2025 |