- input
- $0.10
- cached
- $0.025
- output
- $0.90
- Context
- 262Ktokens
- Released
- 6mo ago
- Size
- 35Bparameters
Cost/1M tokens
Open-weight builds
Ollama variants
Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.
| Variant | Parameters | Type | Quantization | Size | Context | Input |
|---|---|---|---|---|---|---|
| qwen3.6:27b-bf16 | 27B | — | BF16 | 56 GB | 256K | text + image |
| qwen3.6:27b-coding-bf16 | 27B | — | BF16 | 55 GB | 256K | text + image |
| qwen3.6:27b-mlx-bf16 | 27B | — | BF16 | 56 GB | 256K | text + image |
| qwen3.6:27b-mtp-bf16 | 27B | — | BF16 | 56 GB | 256K | text + image |
| qwen3.6:27b-coding-mtp-q4_K_M | 27B | — | Q4_K_M | 18 GB | 256K | text + image |
| qwen3.6:27b-mtp-q4_K_M | 27B | — | Q4_K_M | 18 GB | 256K | text + image |
| qwen3.6:27b-q4_K_M | 27B | — | Q4_K_M | 17 GB | 256K | text + image |
| qwen3.6:27b-mtp-q8_0 | 27B | — | Q8_0 | 30 GB | 256K | text + image |
| qwen3.6:27b-q8_0 | 27B | — | Q8_0 | 30 GB | 256K | text + image |
| qwen3.6:27b | 27B | — | — | 18 GB | 256K | text + image |
| qwen3.6:27b-coding | 27B | — | — | 18 GB | 256K | text + image |
| qwen3.6:27b-coding-mxfp8 | 27B | — | — | 30 GB | 256K | text + image |
| qwen3.6:27b-coding-nvfp4 | 27B | — | — | 19 GB | 256K | text + image |
| qwen3.6:27b-mlx | 27B | — | — | 19 GB | 256K | text + image |
| qwen3.6:27b-mxfp8 | 27B | — | — | 30 GB | 256K | text + image |
| qwen3.6:35b-a3b-bf16 | 35B | — | BF16 | 71 GB | 256K | text + image |
| qwen3.6:35b-a3b-coding-bf16 | 35B | — | BF16 | 70 GB | 256K | text + image |
| qwen3.6:35b-a3b-mlx-bf16 | 35B | — | BF16 | 72 GB | 256K | text + image |
| qwen3.6:35b-a3b-mtp-bf16 | 35B | — | BF16 | 72 GB | 256K | text + image |
| qwen3.6:35b-a3b-coding-mtp-q4_K_M | 35B | — | Q4_K_M | 23 GB | 256K | text + image |
| qwen3.6:35b-a3b-mtp-q4_K_M | 35B | — | Q4_K_M | 23 GB | 256K | text + image |
| qwen3.6:35b-a3b-q4_K_M | 35B | — | Q4_K_M | 24 GB | 256K | text + image |
| qwen3.6:35b-a3b-mtp-q8_0 | 35B | — | Q8_0 | 39 GB | 256K | text + image |
| qwen3.6:35b-a3b-q8_0 | 35B | — | Q8_0 | 39 GB | 256K | text + image |
| qwen3.6:35b-a3b-coding | 35B | — | — | 23 GB | 256K | text + image |
| qwen3.6:35b-a3b-coding-mxfp8 | 35B | — | — | 38 GB | 256K | text + image |
| qwen3.6:35b-a3b-coding-nvfp4 | 35B | — | — | 24 GB | 256K | text + image |
| qwen3.6:35b-a3b-mxfp8 | 35B | — | — | 38 GB | 256K | text + image |
| qwen3.6:35b-a3b-nvfp4 | 35B | — | — | 24 GB | 256K | text + image |
| qwen3.6:latest | 35B | — | — | 23 GB | 256K | text + image |
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.