That kind of result makes me suspicious of benchmaxxing. Qwen 27B is 100x smaller than Opus 4.7. Is it really 100x more parameter-efficient? Two orders of magnitude is hard to believe. I don't have the hardware to run a 27B, but I'm curious what real world use is like. Maybe I'll have to buy some usage on a cloud provider to run my own tests, but this seems fishy to me.
In the local LLM communities there is a lot of respect for the Qwen models, but everyone comes to acknowledge that they do a lot of benchmaxxing after using them. Even at full precision they're never as good as models with similar benchmarks.
Oh, goody goody goody! Can't wait for a Q4M with *MTP* support. Does anyone know if there are plans for it?
I am currently using Qwen 3.6 on RTX 3090 and I have to admit that without MTP it would be too slow to be acceptable for me (30-35 tok/sec without MTP, 60-70 with MTP). Without MTP I would just use OpenRouter and rather pay for speed despite having a capable local setup.
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.
Me too. 35B A3B runs really fast on my MacBook Pro (M4 Max) and is suitable for real-time tasks like dictation post-processing. The dense model is not.
I'm still confused about Qwen 3.6 35B A3B. Everything I read said that the 27B model performs better at coding tasks, so what's the purpose of the 35B model?
AgentWorld is a pretty recent MoE release from the Qwen folks with quite a bit better performance than 3.6, released around the same time as 3.7 Plus/Max, I guess. Not sure why it didn't get more attention, as it is definitely better than 3.6 35B A3B on all dimensions, but especially for agentic use. Still nowhere near the dense models (even 3.6 27B), but clearly an upgrade in the small Qwen MoE line.
KAT Coder is another Qwen 3.6 MoE fine-tune that also improves on 3.6 by a measurable amount.
But, I do hope for a bigger MoE, in the 70B to 120B range, something in the Coder Next lineage. I've got a Strix Halo that isn't getting used to its best ability because the best models all run fine on my faster desktop dual 32GB GPU setup, and they run too slow for comfort on the Strix Halo.
I thought the same. But why claim something so shocking when it can easily be discredited and puts your reputation at risk? If they’re claiming Opus 4.6 level, I expect it to at least match Sonnet 4.6.
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.
If the benchmarks don't lie, this is getting very close to Opus 4.6 capability - which was the turning point for me for when AI was "good enough" that it became very hard to justify not using it.
I'm sure there's some benchmaxxing going on, and some things you get only with a a larger model.
But I'm feeling pretty confident if not by Gemma 5 than by mid 2028 we'll have local models that are almost always as good as Opus 4.6 was and in many cases far better.
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.
27B is a dense model so it will be slower with an MoE (A3B), but should have better quality? I still haven’t found very good uses cases on my M3 Max for dense models. Even if you can find a MTP version, it doesn’t help much, especially if you compare against an MoE with MTP as well.
I have an M4 Max (unfortunately 64GB). I have been running the Qwen 35B A3B one for a while now, after testing and benchmarking a number of models. That one was consistently the best in class for tasks like despamming, E-mail classification, OCR and dictation post-processing. It was also really fast (90 tokens/s).
I'm benchmarking the 3.8 model now, it seems it is better (near-perfect score on my E-mail spam filtering benchmark, best of any model I tested, ever). But it is slow.
One thing I would recommend is keeping an eye on MTP parameters. I tested and benchmarked extensively, and I use `--spec-draft-n-max 2` with llama.cpp. Longer sequences actually decrease overall performance.
As for running, I ended up using llama.cpp and its llama-server, with a bunch of scripts written by AI, because I got tired of LM Studio not implementing the image-related parameters which made gemma4 useless for OCR.
FWIW, Qwen 3.8 27B is actually slower with MTP enabled, unless you generate a lot of code with it (and even then it's not obvious, because you'll likely spend most time thinking).
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?
183 comments
[ 2.5 ms ] story [ 73.6 ms ] threadIf you want Qwen3.8-27B Serving Configs for the DGX Spark vLLM NVFP4 and RTX 4090 llama.cpp GGUF I added the setups here https://x.com/ErdalToprak/status/2088299678085308761?s=20
Opus at home
I hope there also will be a new ~10b variant
Unsloth's GGUF quants are up: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF
I am currently using Qwen 3.6 on RTX 3090 and I have to admit that without MTP it would be too slow to be acceptable for me (30-35 tok/sec without MTP, 60-70 with MTP). Without MTP I would just use OpenRouter and rather pay for speed despite having a capable local setup.
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
https://huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B
KAT Coder is another Qwen 3.6 MoE fine-tune that also improves on 3.6 by a measurable amount.
But, I do hope for a bigger MoE, in the 70B to 120B range, something in the Coder Next lineage. I've got a Strix Halo that isn't getting used to its best ability because the best models all run fine on my faster desktop dual 32GB GPU setup, and they run too slow for comfort on the Strix Halo.
Insane if that is the case. Downloading now!
I'm sure there's some benchmaxxing going on, and some things you get only with a a larger model.
But I'm feeling pretty confident if not by Gemma 5 than by mid 2028 we'll have local models that are almost always as good as Opus 4.6 was and in many cases far better.
I'm benchmarking the 3.8 model now, it seems it is better (near-perfect score on my E-mail spam filtering benchmark, best of any model I tested, ever). But it is slow.
One thing I would recommend is keeping an eye on MTP parameters. I tested and benchmarked extensively, and I use `--spec-draft-n-max 2` with llama.cpp. Longer sequences actually decrease overall performance.
As for running, I ended up using llama.cpp and its llama-server, with a bunch of scripts written by AI, because I got tired of LM Studio not implementing the image-related parameters which made gemma4 useless for OCR.
I saw unsloth has 1bit quants too so I might check that out, anybody have experience with those?