Qwen3.8-3.6-27B Blend
Collection
Junie Local's unofficial JetBrains 50/50 blend of Qwen3.6-27B and Qwen3.8-27B: BF16, GGUF, and MLX weights. • 5 items • Updated • 9
Trade
info-designeree1
AI & ML interests
None yet
Recent Activity
upvoted a collection 14 days ago
Qwen3.8-3.6-27B Blend upvoted a collection about 2 months ago
Qwen3.8 new activity 2 months ago
huggingface/InferenceSupport:amd/Instella-MoE-16B-A3B-ThinkOrganizations
None yet
upvoted a collection 14 days ago
upvoted a collection about 2 months ago
amd/Instella-MoE-16B-A3B-Think
#11381 opened 2 months ago
by info-designeree1
liked 2
models 9 months ago
commented a
paper 9 months ago
upvoted a paper 9 months ago
liked a
model 9 months ago
commented a
paper 10 months ago
upvoted a paper 10 months ago
liked 2
models 11 months ago
nvidia/Orchestrator-8B
➕👍 17
1
#6418 opened 11 months ago
by info-designeree1
liked a
model 11 months ago
NexVeridian/Kimi-Linear-48B-A3B-Instruct-4bit
#6405 opened 11 months ago
by info-designeree1
local, open-source models will play major part in future progress, but we can`t match "1.1M tokens/sec on just one rack of GB300 GPUs in our Azure fleet"
reacted to abidlabs's post with 👍 11 months ago
Post
11609
Why I think local, open-source models will eventually win.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
- 8 replies