← AI Hashrate 中文

Can DGX Spark (GH200 480GB) run Qwen3-Coder-480B-A35B-Instruct?

NVIDIA · 480 GB LPDDR5X · 500 GB/s bandwidth · Alibaba · 480.2B (active 35B) · MoE · model ctx up to 256K

✅ Yes — DGX Spark (GH200 480GB) (480 GB) can run Qwen3-Coder-480B-A35B-Instruct at Q4 (8K)
VRAM: 272.11 GB needed of 480 GB
Speed: ~9.1 tok/s (estimated)
CC · WorkableComposite score: VRAM headroom × 0.5 + tok/s speed × 0.5. Q4 @ 8K context.
CUDA
Buy DGX Spark (GH200 480GB) on Amazon →
Estimates from memory-bandwidth formula; rows marked "measured" override. Methodology.

Fit & speed by quant and context

QuantContextVRAM neededFits?tok/s (decode)
Q44K268.61 GBYes9.1 ± est.
Q48K default272.11 GBYes9.1 ± est.
Q432K293.11 GBYes9.1 ± est.
FP164K964.9 GBNo1.8 ± est.
FP168K default968.4 GBNo1.8 ± est.
FP1632K989.4 GBNo1.7 ± 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
Q4264.11 GB7.0 GB1 GB272.11 GB480 GB
FP16960.4 GB7.0 GB1 GB968.4 GB480 GB

Other GPUs that run Qwen3-Coder-480B-A35B-Instruct

No catalog GPU fully fits Qwen3-Coder-480B-A35B-Instruct at Q4/8K — see the model page for offload estimates. model page

All GPUs for Qwen3-Coder-480B-A35B-Instruct →

Other models for the DGX Spark (GH200 480GB)

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