← AI Hashrate 中文

Can DGX Spark (GH200 480GB) run AI21-Jamba-Large-1.5?

NVIDIA · 480 GB LPDDR5X · 500 GB/s bandwidth · ai21labs · 398.6B · model ctx up to NoneK

CC · WorkableComposite score: VRAM headroom × 0.5 + tok/s speed × 0.5. Q4 @ 8K context.
CUDA

Yes — the DGX Spark (GH200 480GB) (480 GB LPDDR5X) can run AI21-Jamba-Large-1.5. At Q4 with the default 8K context it needs ≈ 299.95 GB VRAM (weights 219.23 GB + KV cache 79.72 GB + 1 GB runtime overhead), which fits within 480 GB. Decode at Q4/8K: ≈ 0.8 tok/s (estimated, batch 1). FP16 needs ≈ 877.92 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology. Buy DGX Spark (GH200 480GB) on Amazon →

Fit & speed by quant and context

QuantContextVRAM neededFits?tok/s (decode)
Q44K260.09 GBYes0.8 ± est.
Q48K default299.95 GBYes0.8 ± est.
Q432K539.11 GBNo1.8 ± est.
FP164K838.06 GBNo0.2 ± est.
FP168K default877.92 GBNo0.2 ± est.
FP1632K1117.08 GBNo0.1 ± est.

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

QuantWeightsKV cacheOverheadTotal neededDGX Spark (GH200 480GB) VRAM
Q4219.23 GB79.72 GB1 GB299.95 GB480 GB
FP16797.2 GB79.72 GB1 GB877.92 GB480 GB

Other GPUs that run AI21-Jamba-Large-1.5

No catalog GPU fully fits AI21-Jamba-Large-1.5 at Q4/8K — see the model page for offload estimates. model page

All GPUs for AI21-Jamba-Large-1.5 →

Other models for the DGX Spark (GH200 480GB)

All models on the DGX Spark (GH200 480GB) →