Loading…
Loading…
Models / IQuest-Coder-V1
2 models (40B to 40B) · ↓ 5.2K downloads a month · from $0.90/h on 2x RTX A6000 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalIQuestLab/IQuest-Coder-V1-40B-Loop-Instruct | vLLM | 80 GB | 93.6 GB | $0.90/h 2x RTX A6000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalIQuestLab/IQuest-Coder-V1-40B-Instruct | vLLM | 80 GB | 93.6 GB | $0.90/h 2x RTX A6000 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").