How will people run DeepSeek Coder v2 236B locally by 2025?
0
Ṁ1kJan 2
50%
Lobotomy levels of quantization (e.g. Q2_K)
50%
Unified memory (e.g. M3 Ultra, Mac Studios)
50%
Non-GPU main memory (e.g. AMD EPYC with 512GB DDR5)
50%
Gaming GPUs in one motherboard (e.g. 4090s)
50%
Tall clustering (e.g. Mac Studios over Thunderbolt)
50%
Wide clustering (e.g. Petals)
50%
HBM FPGA/ASIC dark horse (e.g. AMD rains Versal chips like manna)
DeepSeek Coder v2 is arguably a frontier model from a stellar Chinese team. It has cutting edge efficiency tricks, improved reasoning thanks to extensive code pretraining, and what looks like an excellent math corpus.
It's also an absolute chonker despite being MoE.
What's going to be the path for GPU poors needing to run LLMs in "ITAR mode" without building their own private datacenter or buying NVIDIA racks?
Resolves to as many options that apply, based on public information. If there is no public information resolves based on vibes and a DIY pricing spreadsheet.
(Chinese overlords variant of Llama 3 405B question in case Meta gets cold feet.)
This question is managed and resolved by Manifold.
Market context
Get 
1,000 to start trading!
1,000People are also trading
Related questions
Will DeepSeek release V4 in April 2026?
82% chance
DeepSeek open-source frontier model after 3/23/26?
95% chance
will deepseek-v4 destroy all other models?
1% chance
When will Deepseek V4 be released?
4/6/26
R2 / V4-Thinking (DeepSeek) release date
When will Deepseek R2 be released?
4/29/26
Will Deepseek V4 outperform OpenAI and Anthropic models at coding?
3% chance
Will DeepSeek release a proprietary model for sale before EOY 2026?
23% chance
If DeepSeek releases V4 in 2026, will there be articles about it in NYT, WSJ, and WaPo within two weeks of release?
73% chance
Will DeepSeek R2 be open source?
94% chance