❌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 1347.0 GB of VRAM. H200 only has 141 GB, short by 1206.0 GB. INT4 quantization brings it down to 343.2 GB.

955%
VRAM
Won't fit
Estimated VRAM (fp16)
1347.0 GB
of 141 GB on H200· 1206.0 GB short
Tok/sec
52
TFTT
900ms
Power
490W
Rent on GPUniq marketplace
H200
Live prices from verified providers · billed hourly, no commitment.
Rent now

Memory breakdown (fp16)

Quantization comparison

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

PrecisionVRAMUtilisationFits on H200?
FP16 (full precision)1347.0 GB955%❌Won't fit
INT8 (8-bit)677.8 GB481%❌Won't fit
INT4 / Q4 (4-bit)343.2 GB243%❌Won't fit

Frequently asked

Can H200 run DeepSeek-V3 671B?
Not at fp16 — DeepSeek-V3 671B needs about 1347.0 GB while H200 has 141 GB. It fits at INT4 quantization (343.2 GB) with some accuracy trade-off.
How much VRAM does DeepSeek-V3 671B use?
About 1347.0 GB at fp16, 343.2 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.

Other GPUs for DeepSeek-V3 671B

Other models on H200

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.