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

21–30 of 317 posts

Re: Qwen3.7-Max: The Agent Frontier

#21

Post by throwaw12 »

ttoinou wrote: post #17
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?

M5 Max 64GB (sweet spot) or 128GB (only 1000 USD, better to keep it for the future) more are the best quality price ratio, future proof, reliable, resellable and flexible workloads. Harder to use as a server might be the only drawback

What do you recommend for non-Mac setup? I am a Mac user, but its getting expensive, and not seeing reason to jump to the latest M5

Re: Qwen3.7-Max: The Agent Frontier

#22

Post by tempoponet »

gcr wrote: post #11
smcleod wrote: post #8

Earlier quoted context omitted.

Yeah that 60-150b~ range is such a sweet spot for current 'prosumer' hardware, I'd love to see something like a 120b-a14b or there about.

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 mostly ecosystem, memory bandwidth, and power consumption. They're all slow. The best option is likely to rent hardware on Runpod. The RIO on self-hosting is very low unless you have a specific need or you're ok treating it as a hobby.

Re: Qwen3.7-Max: The Agent Frontier

#23

Post by embedding-shape »

gcr wrote: post #11
smcleod wrote: post #8

Earlier quoted context omitted.

Yeah that 60-150b~ range is such a sweet spot for current 'prosumer' hardware, I'd love to see something like a 120b-a14b or there about.

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?

If I could find a RTX Pro 6000 for $5K I'd definitively grab it, I'm running RedHatAI/Qwen3.6-35B-A3B-NVFP4 on one (I had to pay closer to $10K for it though) with 260K context and it's a blast! ds4 by antirez also works well, even IQ2XXS seems to work relatively well but Qwen3.6-35B-A3B-NVFP4 is both faster and higher quality responses (at least for coding and translations which I use them mostly for).

Re: Qwen3.7-Max: The Agent Frontier

#24

Post by smallerize »

roger_ wrote: post #19
ttoinou wrote: post #17

Earlier quoted context omitted.

M5 Max 64GB (sweet spot) or 128GB (only 1000 USD, better to keep it for the future) more are the best quality price ratio, future proof, reliable, resellable and flexible workloads. Harder to use as a server might be the only drawback

M5 Max 128GB for $1k?

I think they mean the upgrade to 128GB is +$1k.

Re: Qwen3.7-Max: The Agent Frontier

#25

Post by tekacs »

As they start to release more proprietary models, I so wish that they partnered with one of the major US hyperscalers to allow using these models through something US-domiciled.

Totally understand why it may not be reasonable or in their best interest (and that the US is _absolutely_ not doing the same reflexively). But it would be lovely to be able to try these out on production workloads in earnest.

Re: Qwen3.7-Max: The Agent Frontier

#26

Post by Aurornis »

goyozi wrote: post #2

These are very good numbers. I still don’t get why they don’t compare against latest competitor versions in these posts, it’s not like we’re all not going to notice.

I think the argument is that trying to suggest that they’re close to N months from SOTA.

Realistically I assume they hope readers don’t notice the fine details.

The Qwen models are great for open weights but for every past release they haven’t performed as well as the benchmarks in my experience. They’re optimizing for benchmark numbers because they know it works.

Re: Qwen3.7-Max: The Agent Frontier

#27

Post by embedding-shape »

tekacs wrote: post #25

As they start to release more proprietary models, I so wish that they partnered with one of the major US hyperscalers to allow using these models through something US-domiciled. Totally understand why it may not be reasonable or in their best interest (and that the US is _absolutely_ not doing the same reflexively). But it would be lovely to be able to try these out on production workloads in earnest.

Unless US hyperscalers do the same in reverse, I hope the status quo stays as it is. Either people are happy to share, and the sharing should happen both ways, or US hyperscalers can keep isolating themselves as they've done so far.

Re: Qwen3.7-Max: The Agent Frontier

#30

Post by anonym29 »

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…

Bosgame M5 (Strix Halo) w/ 128 GB still goes for $2800 right now. SH systems have surged in price dramatically but quite unevenly.

>The best option is likely to rent hardware on Runpod.

Vast.ai is much cheaper, but the broader point here is contestable. The only dimension in which cloud GPU rentals win is cost. You lose the confidentiality, integrity, and availability benefits of local deployments.

Post reply on HN