Qwen3-Coder

“it gets 40-50 Token/s with 65k context. That is a lot more usable than a Quantised Qwen3.8-27B”

“when an open model (qwen3-coder:30b) drives an mcp tool (chrome-devtools-mcp@latest), it hallucinates the tool calls”

“If you can fire up quantized Qwen 2.5 coder model on your own machine, you control your workflow.”

“at least the most recent versions are getting better but still not quite good enough in real world use cases outside of benchmarks”

“I haven't found another model that performs as well for the specific tasks I was doing with it.”

“I tried out a few models and ended up going with either Qwen3-Coder-Next (no think, just do)”

“I get 6-7 tok/s, which is slow for throwing around program code, but fine for general knowledge queries.”

“check out qwen3.6 coder and heretic models. 30b is the sweet spot for coding and unit testing.”

“qwen 3/3.6 coder is the real champion doing almost the same things with less than 1/10th the memory requirements”

“Worked great and was so stupidly fast it made me realize that if the hardware can be at that level”

“accuracy around function/tool calling hasn't been a problem for me now for about 6 - 12 months, personally, since around QwenCoder3”

“Using opencode and Qwen-Coder-Next I get it reliably up to about 85k before it takes too long to respond.”

“both can get some things done and can waste tons of time getting some things completely wrong”

“Don't think you can throw enough funding at qwen-next-coder to rival Opus at a similar price”

“so much of the tedium of programming is accelerated by the mind-reading autocomplete with 300ms latency”

“QWEN3.5-Next-Coder does wonders. It's drawbacks are time to first token is 30 seconds to load the model”

“it is likely to be the most powerful open weights coding assistant that you can run locally”

“Any of coder-next quants larger than UD-Q4_K_XL take forever to load, especially with ROCm.”

“it's dumb, but if the task is 'clone this component and rewrite it to testWhatever' it does it perfectly well.”

“Coding locally with Qwen3-Coder-Next or Qwen-3.5 is a piece of cake on a workstation card”

“We tend to find Qwen3-Coder-Next better at coding at least on our anecdotal examples from our codebases.”

“it works quite well, both as ChatGPT like chat-interface using llama.cpp and as coding agent”

“I've also seen the occasional tool call looping in Qwen3 Coder Next, that seems to be an easy failure mode for that model to hit.”

“Doing anything beyond basic work will just burn tokens for hours while you review and reject code.”

“it's really not in the same universe with Claude Code, it will be slow and generate bad code.”

“Qwen3-Code is way more likely to do exactly what is being asked than any Gemini model”

“I switched from Claude to Qwen3-Coder-Next for day-to-day on dev projects and don't see a big difference.”

“Qwen3 variants perform very well, speed wise. For local sensitive document work, these are excellent; for serious coding not so much.”

“Got caught in a loop reading a single file over and over again until the context filled up.”

“I tried and it would just bug out, things like respond with JSON strings summarizing what I asked of it or just outright getting things wrong entirely”

“I started swapping once I actually tried to run any queries, and, yeah, could not have a context larger than 8k.”

“GPU for prompt processing, ram for model weights and context length, and it being MoE makes it fairly zippy.”

“I'm asking it to do some analysis/explain some Rust code in a rather large open source project and it's working nicely”

“it's actually seeming pretty competent. These are the first results I've had on a locally hosted model that I could see myself actually using”

“In general UD-Q4_K_XL (Unsloth Dynamic 4bits Extra Large) is what I generally recommend for most hardware”

“widely considered the first open-source model to reach GPT-4o and Claude 3.5 Sonnet levels of coding proficiency”

“the Qwen3-Coder series has emerged as the strongest open-source performer”

“It consistently outperformed (at the time) Gemini 2.5 Pro and Claude Opus 3.5 with its ability to generate and re-factor code”

“I was impressed at how good Qwen3-Coder is. Not as good as Claude, but close - maybe even better in some ways.”

“Qwen3 is really good at hitting the tools first, then coming up with a well-grounded answer based on reality.”