Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen3.7-Max: The Agent Frontier

qwen.ai

Post reply on HN
Print view View original

191–200 of 317 posts

Re: Qwen3.7-Max: The Agent Frontier

#191

Post by wuliwong »

briga wrote: post #109

I was getting dangerously close to my weekly Claude Code limit last night so I had Claude set up Qwen3.6 with llama.cpp and OpenCode. Honestly it's a great (free!) alternative to Claude Code--certainly more than good enough for a lot of smaller less complex tasks. I'm excited to try this new version. The fact that open-source models are so close to the frontier is very impressive.

Do you have a feel for how it Qwen 3.6 compares to Sonnet 4.6? B/C in reality, that's what we use a lot. If we just use Opus 4.7 for everything code related, we'd have a monthly bill 10-20 times higher than using Sonnet where we can.

Re: Qwen3.7-Max: The Agent Frontier

#192

Post by ttoinou »

briga wrote: post #109

I was getting dangerously close to my weekly Claude Code limit last night so I had Claude set up Qwen3.6 with llama.cpp and OpenCode. Honestly it's a great (free!) alternative to Claude Code--certainly more than good enough for a lot of smaller less complex tasks. I'm excited to try this new version. The fact that open-source models are so close to the frontier is very impressive.

Which agentic coding tool and how do you make sure you have prefix consistency ?

Re: Qwen3.7-Max: The Agent Frontier

#193

Post by jampekka »

throawayonthe wrote: post #81
goldenarm wrote: post #61

The non-hallucination rate in AA-omniscience is SOTA, better than Opus 4.7, Gemini 3.1 Pro and GPT5.5! Congrats to the team

referencing this: https://artificialanalysis.ai/evaluations/omniscience?models... (had to add it to the chart, wasn't displayed by default. is it the lowest rate in the datasetor no?)

This counts only incorrect answers though. A model can get 0% hallucination rate just by refusing to answer all questions.

Re: Qwen3.7-Max: The Agent Frontier

#194

Post by booty »

pixelesque wrote: post #150
briga wrote: post #109

I was getting dangerously close to my weekly Claude Code limit last night so I had Claude set up Qwen3.6 with llama.cpp and OpenCode. Honestly it's a great (free!) alternative to Claude Code--certainly more than good enough for a lot of smaller less complex tasks. I'm excited to try this new version. The fact that open-source models are so close to the frontier is very impressive.

Out of interest, what machine and model are you running it on? I tried the qwen3.6-27b Q6_k GUFF in llama.cpp and LM Studio on my M2 MacBook Pro 32GB machine last week, and I barely get a token a second with either. What sort of speed should I be expecting? I tried some of the Llama 3 34b (nous-capybara?) models two years ago with llama.cpp, and I seem to remember getting a few tokens a second then, so not sure if I'…

    I tried the qwen3.6-27b Q6_k GUFF in llama.cpp 
    and LM Studio on my M2 MacBook Pro 32GB machine 
    last week, and I barely get a token a second with either.
The fact that it was this slow makes me suspect it's a matter of insufficient free RAM. The entire model needs to fit into RAM (and stay there the entire time) for acceptable performance.

(not sure of exact diagnosis/fix, but definitely look in that direction if you're still having this issue when you give it another shot)

Also, there are two stages - prompt processing, and token generation. Prompt processing is notoriously slow on Apple Silicon unfortunately. If you have large context (which includes system prompts, lots of tools loaded by a harness like Claude Code, OpenCode, etc) it can take minutes for prompt processing before you see the first output token. On the bright side, the tokens are cached between turns, so subsequent turns won't be so bad.

Re: Qwen3.7-Max: The Agent Frontier

#195

Post by growt »

ecshafer wrote: post #135
briga wrote: post #109

I was getting dangerously close to my weekly Claude Code limit last night so I had Claude set up Qwen3.6 with llama.cpp and OpenCode. Honestly it's a great (free!) alternative to Claude Code--certainly more than good enough for a lot of smaller less complex tasks. I'm excited to try this new version. The fact that open-source models are so close to the frontier is very impressive.

Qwen3.6 with claude code works great. I get a lot better results with that than opencode and qwen3.6. Claude Code is a great harness, and good harness/tool integration makes a big difference. You just have a settings.json with your ollama setup and the qwen model and you can use it.

Where and how do you run that? I tried it but somehow I always ran out of context or generation was incredibly slow (mbp m4 pro 48gb).

Re: Qwen3.7-Max: The Agent Frontier

#196

Post by satvikpendem »

pixelesque wrote: post #150
briga wrote: post #109

I was getting dangerously close to my weekly Claude Code limit last night so I had Claude set up Qwen3.6 with llama.cpp and OpenCode. Honestly it's a great (free!) alternative to Claude Code--certainly more than good enough for a lot of smaller less complex tasks. I'm excited to try this new version. The fact that open-source models are so close to the frontier is very impressive.

Out of interest, what machine and model are you running it on? I tried the qwen3.6-27b Q6_k GUFF in llama.cpp and LM Studio on my M2 MacBook Pro 32GB machine last week, and I barely get a token a second with either. What sort of speed should I be expecting? I tried some of the Llama 3 34b (nous-capybara?) models two years ago with llama.cpp, and I seem to remember getting a few tokens a second then, so not sure if I'…

Check out Unsloth Studio it provides MTP support now which 2x the token generation speed with no loss of accuracy: https://unsloth.ai/docs/models/qwen3.6#mtp-guide

Re: Qwen3.7-Max: The Agent Frontier

#197

Post by tantaman »

rlt wrote: post #128
gslepak wrote: post #115

Earlier quoted context omitted.

> The non-hallucination rate in AA-omniscience is SOTA Note that a perfect "non-hallucination rate" is rather meaningless as such tests can contain human hallucinations. It means the model aligns with the possibly-true, possibly-false beliefs of the group that made the test.

Well, yes, garbage in garbage out. That's a given and not what's meant by "hallucination" in this context.

the observation goes beyond garbage in garbage out. Mainly that we're always operating from some prior and limited understanding. That what may look like a hallucination could be closer to the truth than our current frameworks of understanding allow us to admit. The hermeneutic circle.

Re: Qwen3.7-Max: The Agent Frontier

#199

Post by satvikpendem »

rayboy1995 wrote: post #161
lostmsu wrote: post #111

Earlier quoted context omitted.

Qwen recommends to preserve_thinking: true for agentic/coding workloads.

Thanks!! I had disabled that previously while debugging, I can confirm this is helping accuracy from what I can tell so far. (And speed since the cache is preserved more often!)

Use the MTP models which 2x token generation speed, for example: https://unsloth.ai/docs/models/qwen3.6#mtp-guide

Re: Qwen3.7-Max: The Agent Frontier

#200

Post by dzr0001 »

pixelesque wrote: post #150
briga wrote: post #109

I was getting dangerously close to my weekly Claude Code limit last night so I had Claude set up Qwen3.6 with llama.cpp and OpenCode. Honestly it's a great (free!) alternative to Claude Code--certainly more than good enough for a lot of smaller less complex tasks. I'm excited to try this new version. The fact that open-source models are so close to the frontier is very impressive.

Out of interest, what machine and model are you running it on? I tried the qwen3.6-27b Q6_k GUFF in llama.cpp and LM Studio on my M2 MacBook Pro 32GB machine last week, and I barely get a token a second with either. What sort of speed should I be expecting? I tried some of the Llama 3 34b (nous-capybara?) models two years ago with llama.cpp, and I seem to remember getting a few tokens a second then, so not sure if I'…

My token throughput is much better using vLLM-mlx on my M2 ultra than llama.cpp. It might be worth a shot to give it a try.
Post reply on HN