Qwen 3.8 27B

TomGarden

Really excited to see what people do with this. 3.7 27B was probably the best compromise between size and intelligence to run on consumer hardware

erdaltoprak

This is one of the most important model releases since most use cases don't need SOTA/Frontier If 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

chvid

These are massive improvements - and something you can actually run on a laptop.

brcmthrowaway

My Strix Halo is about to go overdrive!

tosh

27b dense model at Opus 4.6 level Opus at home I hope there also will be a new ~10b variant

scrlk

Beats Opus 4.7 Max (w/ Claude Code) on DeepSWE (42.2 vs 40). Looks like Qwen's 27B models continue to pack some punch. Unsloth's GGUF quants are up: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF

kristopolous

q4km is about 48 tps on a 4090. my llama.cpp params are --flash-attn on --parallel 1 --load-mode mmap

KronisLV

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. Also alternate link for viewing the images without signing in: https://xcancel.com/Alibaba_Qwen/status/2088280182356611304

altruios

remember to let llama.cpp catch up to anything new in this model. Save your judgment until about 2 weeks of use.

expedited123

Kinda was expecting to see Gemma 4 26B in benchmark comparisons :(

anana_

Monstrous benchmarks! Hoping it is not benchmaxxed.

kunver

Welcome deepseek flash flash!

NorwegianDude

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!

onlyrealcuzzo

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.

kunver

Looks like a pretty significant improvement on the DeepSWE benchmark compared to the previous 27B model.

alpha_trion

NICE, i've been waiting for this drop, thanks for posting this

TomGarden

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.

ThouYS

I am so happy right now, qwen3.6-27b was an absolute game changer. To see another one in the same league.. phew

jedbrooke

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?

tosh

also cool: Qwen 3.8 27b is multi modal!