What GPU do I need to run Salesforce/xLAM-8x22b-r?
140.6B parameters, published in BF16. View on Hugging Face
Set up xLAM-8x22b-rxLAM-8x22b-r is published by Salesforce on Hugging Face, with 17,853 downloads and 45 likes to date. It's a MixtralForCausalLM model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 261.9 GB | 314.3 GB | RTX A6000 | 7 | $2.54/hr |
| FP8 (quantized) | 131.0 GB | 157.2 GB | RTX 4000 SFF Ada | 8 | $1.58/hr |
| INT4 (quantized) | 65.5 GB | 78.6 GB | A100 | 1 | $1.21/hr |
| cheaper alt. | RTX 5060 Ti | 5 | $0.550/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run xLAM-8x22b-r at its published (BF16) precision: 7× RTX A6000, at $0.363/hr per GPU ($2.54/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
xLAM-8x22b-r: common questions
Can xLAM-8x22b-r run on a single GPU?
No. At BF16 it needs 314.3 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 48.0 GB RTX A6000, and it takes 7 of them.
How many GPUs do I need to run xLAM-8x22b-r?
7 at BF16. It needs 314.3 GB of VRAM and the cheapest capable live offer is a 48.0 GB RTX A6000, so 7 of them come to $2.54/hr in total.
Does quantizing xLAM-8x22b-r lower the GPU bill?
Yes. At BF16 the cheapest live fit is 7 RTX A6000 cards at $2.54/hr. At INT4 (quantized) it drops to one A100 at $1.21/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Salesforce models
- Llama-xLAM-2-8b-fc-r (8.0B, BF16)
Related reading: RTX A6000 pricing and specs, The NVIDIA Inception program, explained, Google Colab alternatives for dedicated GPU access, Free GPU credits for students and researchers, and RunPod volume disk vs. network volume, compared.
