Local LLM model page

Yi 1.5 (34B)

High-performing bilingual (EN/CN) model. Strong at general tasks. 305K downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
34B
Minimum RAM
24 GB
Model size
20 GB
Quantization
Q5_K_M

Can Yi 1.5 (34B) run locally?

Yi 1.5 (34B) is best suited for power-user machines with 32 GB RAM. LocalClaw recommends Q5_K_M as the default quantization, with at least 24 GB RAM.

Search term for LM Studio or compatible runtimes: yi-1.5-34b-chat

Hugging Face repository: TheBloke/Yi-1.5-34B-Chat-GGUF

chatgeneralpower

Strengths

  • High-performing bilingual (EN/CN) model. Strong at general tasks. 305K downloads.

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • chat
  • general
  • power

Benchmarks

Speed: 4/10

Quality: 8/10

Coding: 7/10

Reasoning: 8/10

Technical details

Developer: yi

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-05