family qwen · 12 variants · unknown
no scores.
| variant | kind | quant | bits | vRAM | dl | org | year |
|---|---|---|---|---|---|---|---|
| Qwen3-Coder-30B-A3B-Instruct | original | bf16 | 16.0 | 1,547,484 | Qwen | 2025 | |
| Qwen3-Coder-30B-A3B-Instruct-FP8 | fp8 | fp8 | 8.0 | 1,434,109 | Qwen | 2025 | |
| Qwen3-Coder-30B-A3B-Instruct-GGUF | gguf | gguf | 16.0 | 1,264,151 | unsloth | 2026 | |
| Qwen3-Coder-30B-A3B-Instruct-MLX-4bit | mlx | mlx | 158,079 | lmstudio-community | 2025 | ||
| Qwen3-Coder-30B-A3B-Instruct-MLX-8bit | mlx | mlx | 141,503 | lmstudio-community | 2025 | ||
| Qwen3-Coder-30B-A3B-Instruct-MLX-5bit | mlx | mlx | 140,681 | lmstudio-community | 2025 | ||
| Qwen3-Coder-30B-A3B-Instruct-MLX-6bit | mlx | mlx | 138,724 | lmstudio-community | 2025 | ||
| Qwen3-Coder-30B-A3B-Instruct-GGUF | gguf | gguf | 3.0 | 69,847 | lmstudio-community | 2025 | |
| Qwen3-Coder-30B-A3B-Instruct | original | bf16 | 16.0 | 30,622 | unsloth | 2026 | |
| Qwen3-Coder-30B-A3B-Instruct-1M-GGUF | gguf | gguf | 16.0 | 10,577 | unsloth | 2025 | |
| Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUF | gguf | gguf | 8.0 | 1,189 | ggml-org | 2025 | |
| Qwen3-Coder-30B-A3B-Instruct-GGUF | gguf | gguf | 16.0 | 322 | Mungert | 2025 |