bartowski / text-generation updated 2 years ago

DeepSeek-Coder-V2-Lite-Instruct-GGUF

Original model: https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

Params
Context
Downloads 30d
461 K
Likes
192
Licence: other Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 26 days
461 K196 K
Aug 27Sep 4Sep 13Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
DeepSeek-Coder-V2-Lite-Instruct-IQ2_S.gguf IQ2_S 6.0 GB 7.1 GB ✅ Runs comfortably
DeepSeek-Coder-V2-Lite-Instruct-IQ2_XS.gguf IQ2_XS 6.0 GB 7.1 GB ✅ Runs comfortably
DeepSeek-Coder-V2-Lite-Instruct-IQ2_M.gguf IQ2_M 6.3 GB 7.5 GB ✅ Runs comfortably
DeepSeek-Coder-V2-Lite-Instruct-Q2_K.gguf Q2_K 6.4 GB 7.6 GB ✅ Runs comfortably
DeepSeek-Coder-V2-Lite-Instruct-IQ3_XXS.gguf IQ3_XXS 7.0 GB 8.2 GB ✅ Runs comfortably
DeepSeek-Coder-V2-Lite-Instruct-IQ3_XS.gguf IQ3_XS 7.1 GB 8.3 GB ✅ Runs comfortably
DeepSeek-Coder-V2-Lite-Instruct-IQ3_M.gguf IQ3_M 7.6 GB 8.8 GB ✅ Runs comfortably
DeepSeek-Coder-V2-Lite-Instruct-IQ4_XS.gguf IQ4_XS 8.6 GB 9.9 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · IQ2_M
$ ollama run deepseek-coder-v2-lite-instruct-gguf

# pin the quantization explicitly
$ ollama run deepseek-coder-v2-lite-instruct-gguf-iq2_m
est. VRAM 7.5 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
other
First seen on the Hub
2024-06-17
Training datasets
undisclosed
Added to our catalog
2026-08-27
Compare with any text-generation model