Can DGX Spark (GH200 480GB) run GLM-4.7-Flash?

NVIDIA · 480 GB LPDDR5X · 500 GB/s bandwidth · Z.ai · 31.2B (active 3B) · MoE · model ctx up to 198K

CUDA

Yes — the DGX Spark (GH200 480GB) (480 GB LPDDR5X) can run GLM-4.7-Flash. At Q4 with the default 8K context it needs ≈ 18.76 GB VRAM (weights 17.16 GB + KV cache 0.6 GB + 1 GB runtime overhead), which fits within 480 GB. Decode at Q4/8K: ≈ 106.1 tok/s (estimated, batch 1). FP16 (≈ 64.0 GB) also fits, at ≈ 29.2 tok/s (estimated). 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

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	18.46 GB	Yes	106.1 ± est.
Q4	8K default	18.76 GB	Yes	106.1 ± est.
Q4	32K	20.56 GB	Yes	106.1 ± est.
FP16	4K	63.7 GB	Yes	29.2 ± est.
FP16	8K default	64.0 GB	Yes	29.2 ± est.
FP16	32K	65.8 GB	Yes	29.2 ± 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

Quant	Weights	KV cache	Overhead	Total needed	DGX Spark (GH200 480GB) VRAM
Q4	17.16 GB	0.6 GB	1 GB	18.76 GB	480 GB
FP16	62.4 GB	0.6 GB	1 GB	64.0 GB	480 GB

Other GPUs that run GLM-4.7-Flash

• B200 192GB SXM — ≈1697.0 tok/s Q4 est.
• MI300X 192GB — ≈1124.2 tok/s Q4 est.
• H200 141GB SXM5 — ≈1018.2 tok/s Q4 est.
• H100 80GB SXM5 — ≈710.6 tok/s Q4 est.
• Gaudi 3 128GB — ≈694.9 tok/s Q4 est.
• A100 80GB SXM4 — ≈432.5 tok/s Q4 est.
• RTX 5090 32GB — ≈380.1 tok/s Q4 est.
• RTX 4090 24GB — ≈213.8 tok/s Q4 est.

All GPUs for GLM-4.7-Flash →

Other models for the DGX Spark (GH200 480GB)

• MiniCPM5-1B — ≈294.6 tok/s Q4 est.
• Qwen3.5-2B — ≈159.1 tok/s Q4 est.
• DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx — ≈138.3 tok/s Q4 est.
• Qwen3.6-35B-A3B — ≈106.1 tok/s Q4 est.
• Qwen3.5-35B-A3B — ≈106.1 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈106.1 tok/s Q4 est.
• Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 — ≈106.1 tok/s Q4 est.
• Qwen3-Coder-Next — ≈106.1 tok/s Q4 est.

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