DE
DeepSeek
Language model · China ·May 2024

DeepSeek-V2 (MoE-236B)

Language Open (Restricted)
236B
Parameters
9
Benchmarks

About DeepSeek-V2 (MoE-236B)

DeepSeek-V2 (MoE-236B) is an AI model developed by DeepSeek, in the language category, released in 2024, made available as an open-weights model with 236B params.

On this page you'll find DeepSeek-V2 (MoE-236B)'s full specifications, including 9 benchmark results. Review provider pricing and benchmark scores below, or compare DeepSeek-V2 (MoE-236B) head-to-head with other language models.

Links

Run DeepSeek-V2 (MoE-236B) locally — what to buy

Share this build ↗

Sized to what DeepSeek-V2 (MoE-236B) actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Software support

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Community

Would you run DeepSeek-V2 (MoE-236B) again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

DeepSeek-V2 (MoE-236B) benchmark scores
Benchmark Category Score Variant
HumanEval code 81.1% cited-telechat2
MBPP code 72% cited-telechat2
AlignBench v1.1 general 7.91 cited-telechat2
C-Eval general 78% cited-telechat2
IFEval general 63.8% cited-telechat2
MMLU general 77.8% cited-telechat2
CMMLU knowledge 81.6 cited-telechat2
GSM8K math 92.2% cited-telechat2
BIG-Bench Hard reasoning 79.7% cited-telechat2

More models like DeepSeek-V2 (MoE-236B)

Frequently asked questions

What is DeepSeek-V2 (MoE-236B)?

DeepSeek-V2 (MoE-236B) is an AI model developed by DeepSeek, in the language category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created DeepSeek-V2 (MoE-236B)?

DeepSeek-V2 (MoE-236B) was developed by DeepSeek and released in 2024.

Is DeepSeek-V2 (MoE-236B) open source or proprietary?

DeepSeek-V2 (MoE-236B) ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does DeepSeek-V2 (MoE-236B) cost?

Pricing for DeepSeek-V2 (MoE-236B) depends on the provider. See the providers table on this page for the latest API rates.

How does DeepSeek-V2 (MoE-236B) perform on benchmarks?

DeepSeek-V2 (MoE-236B) is benchmarked across 9 evaluations on GenAIList, including HumanEval (81.1%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about DeepSeek-V2 (MoE-236B)?