QCRI models
1 QCRI model from QCRI on Hugging Face, from 8.8B to 8.8B parameters, published by QCRI in BF16, with a 4K-token context. The smallest official model, Fanar-1-9B-Instruct, needs about 19.6 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.
Pick a size
One row per official QCRI size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| Fanar-1-9B-Instruct | 8.8B | 19.6 GB | 9.8 GB | 4.9 GB | RTX A5000 | $0.176/hr | 5.9 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Fanar-1-9B-Instruct | 8.8B | BF16 | 19.6 GB | RTX A5000 | $0.176/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.