family qwen · 10 variants · unknown
no scores.
| variant | kind | quant | bits | vRAM | dl | org | year |
|---|---|---|---|---|---|---|---|
| Qwen3-VL-235B-A22B-Instruct | original | bf16 | 16.0 | 1,794,600 | Qwen | 2025 | |
| Qwen3-VL-235B-A22B-Instruct-NVFP4-MLPerf-Inference-Closed-V6.1-FP8-KV | nvfp4 | nvfp4 | 4.0 | 335,330 | nvidia | 2026 | |
| Qwen3-VL-235B-A22B-Instruct-FP8 | fp8 | fp8 | 8.0 | 115,519 | Qwen | 2025 | |
| Qwen3-VL-235B-A22B-Instruct-NVFP4-MLPerf-Inference-Closed-V6.0 | nvfp4 | nvfp4 | 4.0 | 10,408 | nvidia | 2026 | |
| Qwen3-VL-235B-A22B-Instruct-GGUF | gguf | gguf | 16.0 | 7,385 | unsloth | 2025 | |
| Qwen3-VL-235B-A22B-Instruct-NVFP4-MLPerf-Inference-Closed-V6.1 | nvfp4 | nvfp4 | 4.0 | 6,643 | nvidia | 2026 | |
| Qwen3-VL-235B-A22B-Instruct-NVFP4 | nvfp4 | nvfp4 | 4.0 | 4,288 | nvidia | 2026 | |
| Qwen3-VL-235B-A22B-Instruct-1M-GGUF | gguf | gguf | 16.0 | 1,703 | unsloth | 2025 | |
| Qwen3-VL-235B-A22B-Instruct-GGUF | gguf | gguf | 16.0 | 676 | Qwen | 2025 | |
| Qwen3-VL-235B-A22B-Instruct-GGUF | gguf | gguf | 4.0 | 492 | lmstudio-community | 2025 |