Won't fitfp16 · 4K ctx · batch 1

Does H200 run DeepSeek-V3 671B? No at fp16.

At fp16 precision, DeepSeek-V3 671B (671 B MoE parameters) needs roughly 1428.9 GB of VRAM. H200 only has 141 GB, short by 1287.9 GB. INT4 quantization brings it down to 359.2 GB.

>999%
VRAM
Won't fit
Estimated VRAM (fp16)
1428.9 GB
of 141 GB on H200· 1287.9 GB short
Tok/sec
27
TFTT
3498ms
Power
700W
Rent on GPUniq marketplace
H200
Live prices from verified providers · billed hourly, no commitment.
Rent now

Memory breakdown (fp16)

Shared Weights
74.00 GB
Expert Weights
1342.00 GB
KV Cache
1.67 GB
Activations
6.67 GB
Framework Overhead
4.54 GB

Quantization comparison

Lower precision = less VRAM with a small quality trade-off. Quality order: FP16 > INT8 > INT4.

PrecisionVRAMUtilisationFits on H200?
FP16 (full precision)1428.9 GB1013%Won't fit
INT8 (8-bit)715.8 GB508%Won't fit
INT4 / Q4 (4-bit)359.2 GB255%Won't fit

Frequently asked

Can H200 run DeepSeek-V3 671B?
Not at fp16 — DeepSeek-V3 671B needs about 1428.9 GB while H200 has 141 GB. It fits at INT4 quantization (359.2 GB) with some accuracy trade-off.
How much VRAM does DeepSeek-V3 671B use?
About 1428.9 GB at fp16, 359.2 GB at INT4 (for a 4K context, batch size 1). Longer contexts add to KV cache size; larger batches increase activations.
What's the fastest way to run DeepSeek-V3 671B on H200?
Use a production inference engine like vLLM, SGLang, or TensorRT-LLM with paged attention — they cut KV cache 2–3× vs the naive estimate and batch multiple requests efficiently. For H200, enable Flash Attention 2.
Where can I rent a H200?
GPUniq aggregates live H200 offers from verified providers. You can deploy an instance in about a minute and pay hourly with no commitment.
Try it live

Chat with DeepSeek-V3 671B — no setup

Send a prompt and see how DeepSeek-V3 671B responds directly in our chat. No installation, no GPU required to test.

Open in chat
Want to tweak sequence length, batch size, or fine-tuning? Open the full calculator →
None of the common quantization levels fit this model on H200. Consider multi-GPU deployment or a larger card.