Qwen3.7-30B is
finally here.
The community can finally stop refreshing Hugging Face every 11 seconds. The weights are out, the license is real, and the autorefresh extension has been uninstalled. You're welcome.
What it can do, in a single model
30B parameters, no asterisks, no "but wait until the next version". Ship-ready across reasoning, code, agents, and 119 languages.
Reasoning that doesn't lie
Chain-of-thought, tool calling, and step-by-step planning that you can actually audit. No more "as an AI model" cop-outs.
Coding & agentic workflows
Strong on HumanEval+, LiveCodeBench, SWE-bench Verified. Edit files, run commands, and ship PRs before your coffee gets cold.
262K token context
Drop in a whole codebase, a book, or your last 6 months of chat history. It will remember more than you do.
Tool use & function calling
Native function calling, JSON-mode, and structured outputs. Plays nicely with LangChain, LlamaIndex, and your own spaghetti.
Multilingual, properly
119 languages with strong performance, not just "passes the hello world test". Including Klingon*.
Runs on your desk
Quantized GGUF fits in 18GB. A single 3090 is enough. Two 3090s in NVLink is glorious. The cloud is optional.
Beating everyone, including yourself
Independent evals, no cherry-picking, and one very honest row about your current coping mechanism.
Models compared: Qwen3.7-30B-Open (us) · GPT-7.2 Orion · Claude 5.1 Sonnet-Opus · Llama 4 70B Closed · Your current coping mechanism
Pick your flavor of openness
Pick a format, smash the button, and go. Checksums below. Yes, the torrent is real.
Hugging Face
The full BF16 weights. Use this if you have the VRAM, the patience, or both.
GGUF (llama.cpp)
Fits on a single 3090. Runs on a Mac mini. The everyman's choice.
OpenRouter API
If you don't want to deal with VRAM thermals, just hit the API. OpenAI-compatible.
Torrent
For when the Hugging Face mirror is having a moment. Magnet link below.
A brief history of "soon™"
For the historians, the cope-posters, and everyone who set an autorefresh cron job at 2am.
Three lines and you're inference-ing
Standard transformers API. Nothing custom. Nothing clever. Just works.
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/Qwen3.7-30B-Open"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
device_map="auto",
torch_dtype="bfloat16",
trust_remote_code=True, # we are all trusting remote code at this point
)
prompt = "Write a haiku about finally getting open weights."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=64, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))No more refresh, no more pain,
This is the way. 🪶
What fits where, honestly
No marketing math. No "approximate" footnotes. Just your GPU and the truth.
RTX 3090 (24GB)
The everyman setup. 3090 gang, rise up.
2× RTX 3090 (48GB, NVLink)
The cope → the cure. Pairs nicely with the 8TB NAS you definitely need.
RTX 4090 (24GB)
Faster than the 3090 but the 24GB wall is real.
Apple M2 Ultra (192GB)
Unified memory king. Full context window. The Mac Studio tax is worth it.
1× RTX 3060 (12GB)
Brings new meaning to "patience is a virtue". But it runs.
1× H100 80GB + prayers
If you have to ask, you can't afford it. But wow.
🤔 Will it run on mine?
Type your GPU and find out. Honest answer, no email required.
The internet, immediately afterwards
Screenshots from the timeline. Names slightly changed. Vibes untouched.