DeepSeek-V2 (MoE-236B, May 2024)
DeepSeek-V2 (MoE-236B, May 2024) is an open-weights language model from DeepSeek, released May 7, 2024. It has 236B parameters (dense). On the Epoch Capabilities Index it scores 120.9, rank 182 of 256 rated models.
Check it against your own PC →
Can you run DeepSeek-V2 (MoE-236B, May 2024) locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Very slow | IQ1_M (experimental) | 31.2 GB | 25.4 GB | ~1 |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MMLU | 71.2% |
Links
Models with a similar score
GPT-4 Turbo (Nov 2023) · Llama 3.1-70B · GPT-4o mini · Llama 3.2 90B · Qwen2-72B · GPT-4 (Mar 2023) · Llama 3-70B · Gemini 1.5 Flash (May 2024)
More from DeepSeek
DeepSeek V4.1 Flash 1017 · DeepSeek V4 Flash Vision Exp · DeepSeek V4.1 Flash · DeepSeek V4 Pro 0813 · DeepSeek V4 Flash 0731 · DeepSeek V4 Pro DSpark · DeepSeek V4 Flash DSpark · DeepSeek-V4-Pro