I'm a huge open model fan, and have used them since forever, even have daily drivers for on-prem dev, but no. They do not beat opus on real-world usage.
Qwen models are impressively good for what they are, are "good enough" for plenty tasks, can be ran locally on decently priced hardware, and so on. They certainly have their uses, and the field in general has advanced faster than my early expectations. But to compare a 27B model to SotA behemoths from a few months ago is doing everyone a disservice, especially people who pick it up, try to use them just like API models, and leave disappointed and confused. Number goes up on a benchmark isn't it.
spmurrayzzz 40 minutes ago [-]
> They do not beat opus on real-world usage
We have an internal eval that measures performance on tasks for a handful of embedded systems repos for our mmWave radios (mostly Rust, some C for microcontroller stuff). Qwen3.6-27B scores only 4% lower for pass@1, n=250 compared to Opus-4.8.
For the labeled dataset, the average PR size they're being measured against is around 1.5k SLOC.
This is very much "real-world usage" for us. The sort of change sets that come in daily/weekly and are solving non-trivial issues in the respective codebases.
As is usually the case, the most broad claims from both the labs and from the consequent pushback are talking past each other.
KronisLV 42 minutes ago [-]
> ...but no. They do not beat opus on real-world usage.
I agree, but then we just need meaningful benchmarks that clearly show that! Otherwise it's hand waving about something that should be put on paper in quantifiable terms.
pimeys 13 minutes ago [-]
If you are working in a company and using language models, it is a very good idea to hold a bunch of evals you can trust and use to validate new models. Calibrate every once in a while with prod data. We have our own and the only numbers on quality and cost I trust come from this setup.
niek_pas 37 minutes ago [-]
A wise man once said, "not everything that counts can be counted, and not everything that can be counted counts".
bewareofscams 36 minutes ago [-]
Only useful benchmarks are those you (in particular) don't have access to.
xienze 33 minutes ago [-]
> but then we just need meaningful benchmarks that clearly show that!
That's the rub. AI benchmarks are IMO, by and large totally unreliable. We think of them as similar to traditional benchmarks of deterministic processes where the number of variables is low. But they're anything but that. Non-deterministic processes with an astounding number of variables and fuzzy acceptance criteria.
It leads to results like these, where if you take it at face value, the only conclusion you can draw is "wow Anthropic must be stupid if Opus takes 1T parameters to do what Qwen can do in 27B."
It's a bit bare at the moment, I assume they are going to add further detail later, similar to their other releases.
edg5000 1 hours ago [-]
That's crazy, considering the massive size difference. But the small Qwen models are known for punching above their weight.
UncleOxidant 17 minutes ago [-]
Good morning Dario!
KronisLV 1 hours ago [-]
I hope really badly that we'll get a new 35B A3B or similar MoE model!
I also miss the Qwen 3 Coder Next, which was 80B A3B, there are quite a few use cases where a non-dense model <100B would be the sweet spot (when you have the VRAM but not the TDP or compute power). Heck, I'd gladly take A5B or A8B or even A10B as a sort of middle ground.
Same here! Qwen3.6-35B-A3B is the only local model I've found that runs reasonably on my iGPU. Looks like me and and my noisily-wheezing laptop will be sitting out this upgrade.
Casteil 55 minutes ago [-]
I'm hoping too that they'll put out some MoE variants.
Qwen3.5:122b:a10b can run about twice as fast as this 27b dense model.
Alifatisk 35 minutes ago [-]
> I'd gladly take A5B or A8B or even A10B as a sort of middle ground.
Whats up with focusing on the active param count? Do yall fiddle with the weights or something?
martinald 30 minutes ago [-]
You can run these on CPUs at a somewhat reasonable speed.
KronisLV 9 minutes ago [-]
Or (somewhat) low TDP GPUs for that matter, like workstation ones, that might have enough total VRAM but not the best bandwidth/compute.
ramon156 32 minutes ago [-]
People will claim it's not comparable to Opus despite it beating the score. I'm not sure I disagree, but I'm also unsure whether I care. Most new models nowadays are "good enough". I cannot complain because I'd rather spend that time improving my prompts and docs. Opus might be a _slight bit better_ at picking up vague hints, but it's also extremely expensive, and I hit the 5 hour limit way too quick.
I care a lot about speed and efficiency right now. For my setup I would like to have 2-3 different model families. I've settled on GLM-5.3 (formerly Deepseek v4 pro 0813) for architecting, Deepseek V4 Pro 0813 for developing, and Gemini flash lite (any recent cheap model) for repo scouting. I'll add another one in the mix for reviewing (in this case Gemini 3.7) and that's all I need.
I've tried most models except Grok.
Qwen is too expensive IMO (Alibaba Cloud subscriptions are hard to come by and I'm not spending 50 euros a month for a tool, so 18 euros it is). If it ever becomes efficient enough to run locally I will definitely look back.
Claude is slow and expensive (the cache hit prices are absurd).
OAI is pretty good, I might add it to my arsenal seeing how cheap it is.
These opinions change every day. Last week I would've never picked Deepseek until I read about the pricing. even post aug 16 it's worth it (although it's getting close to gemini pricing).
Right now my costs are 12 euros a month (z.ai) + whatever deepseek consumes. This typically isn't more than 8 euros a week. 44 euros a month and I have a setup that is doing pretty well.
tosh 4 minutes ago [-]
i think you will like luna if you haven't tried it yet
simplyluke 8 minutes ago [-]
I'm convinced a lot of the anti-open-weight model comments at this point are inorganic traffic - there's trillions in investor money riding on a world where these models aren't cheap commodities. Having actually used things like the recent GLM, Kimi, and Qwen I think any edge the labs have is marginal at most and actually prefer the open weight models in most day to day usage.
Anthropic's recent releases are wordy to the point of exhaustion. Every time I use opus recently I find myself wanting to yell "GET TO THE POINT" at a terminal, which is exacerbated by it being slow.
hypfer 29 minutes ago [-]
> I've settled on GLM-5.3 (formerly Deepseek v4 pro 0813) for architecting
Dude, GLM-5.3 released _today_.
The phrasing "I've settled on" is incorrect for this context.
ramon156 28 minutes ago [-]
hence the "former deepseek v4 pro". I tried it out this morning and have had no complaints. I already liked glm 5.2
hypfer 26 minutes ago [-]
The sentence still doesn't make sense, because "settled on" implies a long testing phase with a verdict eventually emerging out of that.
What you're currently doing is "testing out"
Casteil 10 minutes ago [-]
One thing a lot of people don't seem to factor when hyping Qwen is how much models like this tend to 'overthink' with seemingly endless 'second guessing'. 3.8 seems no different from what I've tried thus far.
As capable as it is, it's hard to justify using it when a competing model (e.g. Gemma4:26b-a3b) can consistently achieve the same or similar response with only 1/10th as many 'thinking' tokens, achieve much higher tokens/second, and take a small fraction of the time. I suppose 'YMMV' depending on your use case.
Also, I haven't used it enough yet to see if it's prone to infinite looping, but its predecessors sure were.
ThouYS 24 seconds ago [-]
gemma4 can't hold a candle to 3.6
lrvick 6 minutes ago [-]
Use 3.6 27b as a daily driver for months with charmbracelet crush. Gemma 26b-A3b is not even remotely comparable in terms of coding for me. YMMV depending on how you work, what harness you use, etc I suppose.
minimaltom 4 minutes ago [-]
Architecture thread! Afaict they continue to use gated attention + delta net, which was also adopted+adapted by K3, but im surprised theres no improvements to the residual stream (deepseek are using manifold hyper-connections, kimi have attention residuals) ?
I hope the bonsai team makes another 1bit quant of this model (or releases code/instructions on how to do it), using the Qwen3.6 27B on my 16GB mac mini has been wild . The 1bit quant feels like opus level… for the first couple turns. Then it has trouble eg switching from plan mode to act mode. This is mostly mitigated by starting a new session. (tbf this limitation is called out on the hf page)
I saw unsloth has 1bit quants too so I might check that out, anybody have experience with those?
TomGarden 58 minutes ago [-]
Any tips on the best approach at running this at an M4 Max 128GB? Token throughput was a bit slow with the last 27B one (MLX), ended up using the A3B variant but if I could get this one to reasonable speed I'd much prefer it.
UncleOxidant 8 minutes ago [-]
Wait for the MTP variants that will likely be out within days. I'm on a 128GB Strix Halo box and for 3.6-27B 8bits I was getting about 9tok/sec (not great). With MTP that gets closer to 18 tok/sec (kind'a usable).
mft_ 46 minutes ago [-]
Go for a slightly more quantised version, and experiment with different MTP settings. I find that MLX versions are marginally faster on my 64GB M1 Max, but I usually use Unsloth's GGUFs via llama.cpp as there's a much greater range of quants available and I prefer llama.cpp. MTP sometimes also helps a little, but I suspect it's less helpful on my system than others.
This is the way if you need speed. It costs a little bit in smarts, but compare the MTPLX option listed above with the oQ4e-mtp quant using oMLX. The good cacheing layer in oMLX will help things feel faster for some classes of tasks in my experience.
LoganDark 51 minutes ago [-]
Unfortunately, that chip just doesn't really have the memory bandwidth to run this (or nearly any) model at acceptable speeds. I have the exact same chip (M4 Max 128GB) and I've been trying to optimize a completely purpose-built implementation with Fable and this is just not possible. Even if you could reach the full 576GB/s, it's just physically impossible to exceed these numbers with the model's architecture:
2 bpw - ~85.7t/s
3 bpw - ~58.0t/s
4 bpw - ~43.9t/s
6 bpw - ~29.5t/s
8 bpw - ~22.2t/s
16 bpw - ~11.2t/s
without cheating. You'd have to exclude layers, skip operations, etc. basically do stuff the model wasn't trained for. And speed collapses so fast with context that even 2 bpw would be looking at ~37.6t/s after just 128K tokens.
MTP only improves the situation by up to 2x in the ideal case, while drastically reducing the performance floor. While optimizing a 9B model on this hardware, I've found that the GPU just doesn't have enough FLOPS to handle speculating more than one or two tokens ahead on a single stream, regardless of quant level, simply because of the arithmetic cost of the forward pass. The 27B model would be even more expensive than that, potentially such that it's already bottlenecked by the GPU itself rather than memory.
I wouldn't get my hopes up for the 35B-A3B either. Not only is it reportedly much less intelligent, but I hit the exact same 85t/s wall in practice (again with highly specialized inference).
Without speculation I can reach around 120t/s on Qwen3.5-9B and with n-gram speculation (not even MTP; this derivative didn't come with one) around about 150t/s on average. This is on the very very edge of what I'd consider acceptable for me to even consider using such a compact model. YMMV due to the silicon lottery but the situation isn't good.
If the benchmarks are a real indication, we now have a local model that is runnable on a high-end personal PC that trades blows with the leading model Claude Opus 4.6 Max from half a year ago.
Insane if that is the case. Downloading now!
tosh 1 hours ago [-]
27b dense model at Opus 4.6 level
Opus at home
I hope there also will be a new ~10b variant
UncleOxidant 6 minutes ago [-]
I'm hoping for a 3.8-122B MoE
yassa9 41 minutes ago [-]
can you tell me ideas of usecases of 9 or 10B language models ? I cant find any usecases other than training a lora on them to give good bash commands for example
mring33621 5 minutes ago [-]
9B Qwen models are good and fast for local python coding tasks.
tosh 25 minutes ago [-]
they are all overlapping but:
categorization, information retrieval, semantic search, image description
also with the model as part of an agentic system with tool calling
(edit: it is quite impressive what a small model in a feedback loop can do)
theanonymousone 33 minutes ago [-]
I'm wondering whether any provider can offer this for cheaper $/token than the new DSv4 Flash, which is both cheaper and smarter :/
Completely local use is a different story, of course.
mickeyp 43 minutes ago [-]
Model benchmarks are useful, to a point, but it is the long tail of things you do with the model that determines if it's good at a wide range of activities. Ant/OAI, to their credit, build their models -- even the small ones -- so they follow instructions and do tool calling well, without the system prompts confusing them. This is especially important for long-horizon tool calling.
So one open weight model might "meet" Opus or whatever on benchmarks, but then fail to follow a simple answer format and also tool call correctly. The models are whipped to within an inch of their lives to strictly adhere to their post training quality gates.
chvid 1 hours ago [-]
These are massive improvements - and something you can actually run on a laptop.
jlkivey 24 minutes ago [-]
Note: on the model card the comparison to Opus is Opus 4.6 Max, not 4.7
yassa9 39 minutes ago [-]
Can anyone who has that specific personal test he tries on different models , and tries this model , to tell us here if possible , how good or bad is this new model ? compared to others ?
I only trust those users genuine personal tests
alyandon 35 minutes ago [-]
There is a down to earth guy on YT that performs a series of tests against LLMs running on non-god-tier commodity hardware. He will likely be testing this soon enough.
strong visual reasoning apparently, which is nice. still lacking native audio however. hoping for more companies to embrace the spirit of something like `gemma-4-12b-qat` for actual multi-modality (text, image, video, audio).
brcmthrowaway 1 hours ago [-]
My Strix Halo is about to go overdrive!
ramon156 46 minutes ago [-]
need another fable uncensored merge with 3.8, really curious what it can deliver
Unsloth's GGUF quants are up: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF
I'm a huge open model fan, and have used them since forever, even have daily drivers for on-prem dev, but no. They do not beat opus on real-world usage.
Qwen models are impressively good for what they are, are "good enough" for plenty tasks, can be ran locally on decently priced hardware, and so on. They certainly have their uses, and the field in general has advanced faster than my early expectations. But to compare a 27B model to SotA behemoths from a few months ago is doing everyone a disservice, especially people who pick it up, try to use them just like API models, and leave disappointed and confused. Number goes up on a benchmark isn't it.
We have an internal eval that measures performance on tasks for a handful of embedded systems repos for our mmWave radios (mostly Rust, some C for microcontroller stuff). Qwen3.6-27B scores only 4% lower for pass@1, n=250 compared to Opus-4.8.
For the labeled dataset, the average PR size they're being measured against is around 1.5k SLOC.
This is very much "real-world usage" for us. The sort of change sets that come in daily/weekly and are solving non-trivial issues in the respective codebases.
As is usually the case, the most broad claims from both the labs and from the consequent pushback are talking past each other.
I agree, but then we just need meaningful benchmarks that clearly show that! Otherwise it's hand waving about something that should be put on paper in quantifiable terms.
That's the rub. AI benchmarks are IMO, by and large totally unreliable. We think of them as similar to traditional benchmarks of deterministic processes where the number of variables is low. But they're anything but that. Non-deterministic processes with an astounding number of variables and fuzzy acceptance criteria.
It leads to results like these, where if you take it at face value, the only conclusion you can draw is "wow Anthropic must be stupid if Opus takes 1T parameters to do what Qwen can do in 27B."
So advantage is not having to produce your own quantisation / gguf from .safetensors you've linked.
Run the one you linked if you are running vllm (safetensors)
It's a bit bare at the moment, I assume they are going to add further detail later, similar to their other releases.
I also miss the Qwen 3 Coder Next, which was 80B A3B, there are quite a few use cases where a non-dense model <100B would be the sweet spot (when you have the VRAM but not the TDP or compute power). Heck, I'd gladly take A5B or A8B or even A10B as a sort of middle ground.
Also alternate link for viewing the images without signing in: https://xcancel.com/Alibaba_Qwen/status/2088280182356611304
Qwen3.5:122b:a10b can run about twice as fast as this 27b dense model.
Whats up with focusing on the active param count? Do yall fiddle with the weights or something?
I care a lot about speed and efficiency right now. For my setup I would like to have 2-3 different model families. I've settled on GLM-5.3 (formerly Deepseek v4 pro 0813) for architecting, Deepseek V4 Pro 0813 for developing, and Gemini flash lite (any recent cheap model) for repo scouting. I'll add another one in the mix for reviewing (in this case Gemini 3.7) and that's all I need.
I've tried most models except Grok.
Qwen is too expensive IMO (Alibaba Cloud subscriptions are hard to come by and I'm not spending 50 euros a month for a tool, so 18 euros it is). If it ever becomes efficient enough to run locally I will definitely look back.
Claude is slow and expensive (the cache hit prices are absurd).
OAI is pretty good, I might add it to my arsenal seeing how cheap it is.
These opinions change every day. Last week I would've never picked Deepseek until I read about the pricing. even post aug 16 it's worth it (although it's getting close to gemini pricing).
Right now my costs are 12 euros a month (z.ai) + whatever deepseek consumes. This typically isn't more than 8 euros a week. 44 euros a month and I have a setup that is doing pretty well.
Anthropic's recent releases are wordy to the point of exhaustion. Every time I use opus recently I find myself wanting to yell "GET TO THE POINT" at a terminal, which is exacerbated by it being slow.
Dude, GLM-5.3 released _today_.
The phrasing "I've settled on" is incorrect for this context.
What you're currently doing is "testing out"
As capable as it is, it's hard to justify using it when a competing model (e.g. Gemma4:26b-a3b) can consistently achieve the same or similar response with only 1/10th as many 'thinking' tokens, achieve much higher tokens/second, and take a small fraction of the time. I suppose 'YMMV' depending on your use case.
Also, I haven't used it enough yet to see if it's prone to infinite looping, but its predecessors sure were.
Perf improvements seem to all come from training?
I saw unsloth has 1bit quants too so I might check that out, anybody have experience with those?
Unsloth: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF
This might work for you, but I didn't get on very well with MTPLX when I tried it a while back; YMMV: https://huggingface.co/Youssofal/Qwen3.8-27B-MTPLX-Optimized...
2 bpw - ~85.7t/s
3 bpw - ~58.0t/s
4 bpw - ~43.9t/s
6 bpw - ~29.5t/s
8 bpw - ~22.2t/s
16 bpw - ~11.2t/s
without cheating. You'd have to exclude layers, skip operations, etc. basically do stuff the model wasn't trained for. And speed collapses so fast with context that even 2 bpw would be looking at ~37.6t/s after just 128K tokens.
MTP only improves the situation by up to 2x in the ideal case, while drastically reducing the performance floor. While optimizing a 9B model on this hardware, I've found that the GPU just doesn't have enough FLOPS to handle speculating more than one or two tokens ahead on a single stream, regardless of quant level, simply because of the arithmetic cost of the forward pass. The 27B model would be even more expensive than that, potentially such that it's already bottlenecked by the GPU itself rather than memory.
I wouldn't get my hopes up for the 35B-A3B either. Not only is it reportedly much less intelligent, but I hit the exact same 85t/s wall in practice (again with highly specialized inference).
Without speculation I can reach around 120t/s on Qwen3.5-9B and with n-gram speculation (not even MTP; this derivative didn't come with one) around about 150t/s on average. This is on the very very edge of what I'd consider acceptable for me to even consider using such a compact model. YMMV due to the silicon lottery but the situation isn't good.
Insane if that is the case. Downloading now!
Opus at home
I hope there also will be a new ~10b variant
categorization, information retrieval, semantic search, image description
also with the model as part of an agentic system with tool calling
(edit: it is quite impressive what a small model in a feedback loop can do)
Completely local use is a different story, of course.
So one open weight model might "meet" Opus or whatever on benchmarks, but then fail to follow a simple answer format and also tool call correctly. The models are whipped to within an inch of their lives to strictly adhere to their post training quality gates.
I only trust those users genuine personal tests
https://www.youtube.com/@lukesdevlab
I don't know if that is what you are looking for or not and as always your experiences may be different.
on my dual 3090s qwen 3.5 27b was running at around 110tps using the config from https://github.com/noonghunna/club-3090
make that 200tps on a single 5090, 4x faster than opus https://x.com/radixark/status/2088285681131110446
devs about to get handed a two 5090 box each and told to max that out
my prediction was way too far out. 4.6 at home! Woo.