Jamba models

3 Jamba models from ai21labs on Hugging Face, from 3.0B to 51.6B parameters, published by ai21labs in BF16, with a 256K-token context. The smallest official model, AI21-Jamba2-3B, needs about 6.8 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Pick a size

One row per official Jamba size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
AI21-Jamba2-3B3.0B6.8 GB3.4 GB1.7 GBRTX 3070$0.088/hr0.03 GB
AI21-Jamba-Reasoning-3B3.2B7.1 GB3.6 GB1.8 GBRTX 3070$0.088/hr0.03 GB
Jamba-v0.151.6B115 GB57.6 GB28.8 GBAMD MI300X$2.63/hr0.50 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 (3)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
AI21-Jamba2-3B3.0BBF166.8 GBRTX 3070$0.088/hr
AI21-Jamba-Reasoning-3B3.2BBF167.1 GBRTX 3070$0.088/hr
Jamba-v0.151.6BBF16115 GBAMD MI300X$2.63/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.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.