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

171–180 of 317 posts

Re: Qwen3.7-Max: The Agent Frontier

#171

Post by mft_ »

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'…

The 27B model is dense, so is relatively slow. The 35B-A3B model is marginally weaker but being MoE is much faster - like ~4-8x faster in basic benchmarks on my M1 Max.

For comparison, I just ran a couple of quick benchmarks (default settings) with llama-bench:

Qwen3.6-35B-A3B at Q6_K_XL gave 858 t/s pp512 (prompt processing) and 43 t/s tg128 (token generation).

Qwen3.6-27B at Q4_K_XL gave 103 t/s pp512 and 8 t/s tg128.

Re: Qwen3.7-Max: The Agent Frontier

#172

Post by jcheng »

gslepak wrote: post #115
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

> 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.

Here are some examples of the questions in the benchmark. If these are representative, they seem pretty cut and dry. https://artificialanalysis.ai/evaluations/omniscience#exampl...

Re: Qwen3.7-Max: The Agent Frontier

#173

Post by bel8 »

cft wrote: post #134

Downloading this and cancelling Google Antigravity Pro at the same time: I had a Google Pro account that I inherited from buying a Pixel 9 XL - it's free for a year after a flagship Pixel phone purchase. After a year they started charging for it, and i tolerated it, because Flash was usable in Antigravity for dumb auxiliary tasks that I did not want to waste GPT/Opus on. It had a separate generous quota from Gemini 3…

same boat. Google Pro AI quota became barely useful for anything meaningful.

I think they envision Pro plan as "just a taste of AI, enough to lure folks into the Ultra plan" but that won't work for me when Codex is half the price and DeepSeek 4 Flash is 1/10 of their price per task.

So I'll downgrade just enough to keep my Google Drive space. And use DeepSeek 4 as workhorse plus Codex or Copilot for advanced stuff.

Re: Qwen3.7-Max: The Agent Frontier

#174

Post by hadlock »

Aurornis wrote: post #60
epolanski wrote: post #58

Earlier quoted context omitted.

> Realistically I assume they hope readers don’t notice the fine details. The pool of people reading such articles while ignoring such details can't be big.

I disagree. Most people skim articles, not read them deeply. On Hacker News I wonder if most people even opened the article at all most times.

Slashdot coined RTFA in the 90s, what you're suggesting isn't a new concept by any measure

e: which itself is a modification of RTFM from usenet

Re: Qwen3.7-Max: The Agent Frontier

#175

Post by kolinko »

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.

As Opus maximalist ;) I was very surprised by the quality if Qwen3.6-27B - trying to figure out how to get it going on RTX 90k now to offload some lighter tasks :)

Re: Qwen3.7-Max: The Agent Frontier

#176

Post by solenoid0937 »

varispeed wrote: post #48
bratao wrote: post #4

It is super strange that all last (3?) releases they keep comparing older models such as Opus-4.6.

Opus-4.6 was probably the best model so far before it got nerfed. 4.7 is nowhere near experience I had. In fact I stopped using it completely because more often than not its output is just dumber than local models.

Opus 4.6 was never nerfed, that's FUD. There were harness-level problems that were fixed.

4.7 is much better. But perception is a funny thing, once you think something is bad you start looking for it everywhere.

Re: Qwen3.7-Max: The Agent Frontier

#177

Post by gcr »

krzyk wrote: post #146
barbacoa wrote: post #121

Earlier quoted context omitted.

Try looking into Ryzen AI Max 395. AMD made a CPU/GPU soc with unified memory specifically for ai inference. Can buy mini PCs with up to 128gb ram.

Isn't CUDA/nvidia the go to solution for most local models, with the rest being second class citizents?

Depends. ROCm is pretty well-supported for example.

Non-NVIDIA backends tend to get less support and new features land slower, or features that are expected to improve performance wind up hurting it instead. That sort of thing.

For basic “token in/token out” workloads without fine tuning, it’s probably fine ??

Re: Qwen3.7-Max: The Agent Frontier

#178

Post by julianlam »

gcr wrote: post #160
pixelesque wrote: post #150

Earlier quoted context omitted.

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'…

There are two flavors of Qwen 3.6: - A 27B "dense" model - A 35B "Mixture of Experts" model, which activates only 3B parameters for each token. For your hardware, I strongly recommend `unsloth/Qwen3.6-35B-A3B-GGUF:Q4_K_M`. I have an M1 Max with 32GB VRAM from 2021 that can read at ~300-500 tokens/sec and write at ~30 tokens/sec with llama-cpp's default settings, which is plenty fast. The 27B model can read ~70tok/sec…

May I ask why the M instead of XL?

Obviously bigger != better but I don't know what the differences are.

Re: Qwen3.7-Max: The Agent Frontier

#180

Post by bahmboo »

tempoponet wrote: post #22
gcr wrote: post #11

Earlier quoted context omitted.

What’s the price point for getting into that sweet spot? I’m on an M1 Max with 32GB VRAM, so I’m looking forward to the 27B or 35B-A3B models. Is dropping $5k for an RTX 6000 or a DGX Spark really the best option?

Expect to pay $4k-10k - Your RTX 6000 is closer to $10k now - Sparks are creeping into the $4-5k range - AMD Strix are ~3.5k - Apple depends on chipset and memory. Sweet spot would be 128gb M3 Ultra, probably $6-8k but admittedly haven't been tracking closely. New M5 might come in the fall. You can get a new 128gb M5 Max laptop for ~5-6k today. - a 4x3090 rig would take $5-6k Every platform has tradeoffs, but it's mo…

$2600 gets MBP M5 Pro 48gb. 64gb requires a Max which bumps it to $4200 at which point you may as well spend the $800 to go to 128gb.
Post reply on HN