arcflare_
Code16B official

deepseek-coder-v2-lite

by DeepSeek

DeepSeek-Coder-V2-Lite: a 16B mixture-of-experts coder with a long context. Cheap to run for its size.

#code#moe#long-context
arcflare pull bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

deepseek-coder-v2-lite

DeepSeek-Coder-V2-Lite: a 16B mixture-of-experts coder with a long context. Cheap to run for its size.

Get it

arcflare pull bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
arcflare run deepseek-coder-v2-lite-instruct

ArcFlare reads the GGUF header and loads it at the largest context your free VRAM can actually hold. Use arcflare fit to see that before downloading anything else, or arcflare use opencode to code with it.

Highlights

  • MoE: far fewer parameters active per token than its 16B total
  • Long context for whole-file and multi-file work
  • DeepSeek's own model licence: commercial use allowed, with use-based restrictions

Sizes

  • 16b · 10.4GB

Other sizes live in sibling repos: swap the size in the repo name when pulling.

[ 03 ] // relatedmore →

glm4.7-flash

Z.ai

Code

GLM-4.7-Flash: a 30B-A3B MoE built for agentic coding. Only ~3B parameters active per token, so it runs at small-model speed.

size
30B-A3B
vram
~20 GB
license
MIT

83% of a 24 GB card

#code #agentic #moe

qwen3-coder-next

Alibaba Qwen

Code

Qwen3-Coder-Next: an 80B MoE with only 3B active, a 256K context, and training aimed at agent harnesses like Claude Code and Cline.

size
80B-A3B
vram
~52 GB
license
Apache-2.0

2.2× a 24 GB card

#code #agentic #moe

qwen3-coder

Alibaba Qwen

Code

Qwen3-Coder 30B-A3B: an agentic coding MoE with 256K context that runs at small-model speed on one GPU.

size
30B-A3B
vram
~19 GB
license
Apache-2.0

79% of a 24 GB card

#code #agentic #moe