- input
- $0.00
- output
- $0.00
- Context
- 262Ktokens
- Listed
- 3w ago
- Size
- 40Bparameters
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 |
|---|---|---|---|---|---|---|
| flint:40b-a2b-mlx-bf16 | 40B | — | BF16 | 80 GB | 256K | text |
| flint:40b-a2b-q4_1 | 40B | — | Q4_1 | 26 GB | 256K | text |
| flint:40b-a2b-gguf-nvfp4 | 40B | — | — | 23 GB | 256K | text |
| flint:40b-a2b-qat-int4 | 40B | — | — | 23 GB | 256K | text |
| flint:latest | 40B | — | — | 23 GB | 256K | text |
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.