Every published setup that reports this model, with its machines, quantization, runtime and reported results. Use the directory filters below to narrow by quantization, capacity or runtime.
Observed across 10 published setups. Counts describe what contributors run, not what the model is “good for”.
Capacity is the reported total for this setup. Multi-GPU and unified-memory layouts can behave differently.
A custom 4x RTX 5090 build with 128GB of VRAM, an Intel Xeon w5-3423 and 192GB of ECC DDR5 runs DeepSeek V4 Flash, Qwen 3.8 and Gemma 4 32B locally for a 50-person company that wants its data off grid.
With access to both Claude Fable and high-end local models, this developer chooses local because a less autonomous model keeps him involved in debugging and research work.
A four-DGX-Spark cluster under vLLM serves several concurrent agentic coding and research sessions, with unquantized weights and honest notes on concurrency limits.
A custom Linux workstation with an RTX Pro 6000 and 48GB of RAM runs programming, copy editing and summarisation through vLLM, with no cloud use all year.
A researcher runs Qwen 3.8 Flash Next and Gemma 4 31B on a 128GB Strix Halo, splitting strategy and summarisation across models and advising against 64GB machines.
After experimenting, this user argues a real computer-manipulating agent needs at least a Strix Halo plus an oculink R9700, or a DGX Spark plus a second GPU for auxiliary models.
A 512GB M3 Ultra Mac Studio running models through oMLX handles most agentic coding work, with measured speeds across several models listed by the owner.
Beyond the obvious coding use case, this setup handles website debugging, deep web research, and day-to-day Linux server maintenance.
Purpose-built tools around a personal research corpus, plus Hermes as an interactive research assistant, get this researcher roughly 80% of the way to frontier quality — locally.
Client confidentiality rules out cloud APIs for this freelancer, who spreads different model sizes across three separate machines.
