Qwen/Qwen3-Coder-Next · Hugging Face
huggingface.co
We’re on a journey to advance and democratize artificial intelligence through open source and open science.

It’s out!

  • cecilkorik@lemmy.caEnglish
    1·
    6 hours ago

    Seems pretty good, using the latest version of ollama (downloaded the default Q4 from ollama) and then popped it into Codex with this config.toml:

    model = "qwen3-coder-next:Q4_K_M"
model_provider = "ollama"
model_reasoning_effort = "medium"

[model_providers.ollama]
name = "Ollama"
base_url = "http://localhost:11434/v1"

[analytics]
enabled = false

    Works well in Codex CLI and VScode Codex IDE plugin. Did not work well with Kilo Code or Roo plugins unfortunately (but I have yet to find much that does).

    I am not an expert, this may not be the best way, I don’t know… just sharing my experience for the other non-experts out there.

  • tpWinthropeIII@lemmy.worldEnglish
    1·
    10 hours ago

    I had trouble with two Unsloth quants and had to switch to Bartowski’s quant.

    IMO it’s a very good model, not just for coding. It’s also very good as a general model. I might even prefer it to instruct.

  • Xylight‮@lemdro.idEnglish
    1·
    2 days ago

    thanks to the beauty of mixture-of-experte models i can shove a q2 quant of this into my 8gb vram

  • zaidka@lemmy.caEnglish
    3·
    6 days ago

    Looks like a solid model based on my limited testing. Though tool calls frequently fail with “JSON parse error” in longer sessions in OpenCode and llama.cpp. Hoping that will be addressed soon.

    • robber@lemmy.mlOPEnglish
      1·
      4 days ago

      Yeah I enjoy it as well. Just in case you missed it - a fix was merged into llama.cpp two days ago which is said to improve quality.

      Edit: I stand corrected - the fix for the issue you’re experiencing has not yet been merged.

  • Avid Amoeba@lemmy.caEnglish
    5·
    8 days ago

    What does this active parameters business about? Is it supposed to perform similar to much bigger models at the same RAM usage?

    • hendrik@palaver.p3x.deEnglish
      7·
      8 days ago

      As far as I know fewer active parameters means faster. There’s less arithmetic calculations to be done per pass. But all parameters need to be kept in memory, because they might become active the next pass. So it won’t save any RAM.

      They have a short paragraph in the description. It has 80B total parameters, 3B active each pass. It achieves performance like a 30-60B model (10-20x, their claim). But is way more efficiant than that with only 3B active parameters.