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 27 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 small ISP (~7,600 customers) serves its agentic operations work on two identical machines, each with 4× RTX 3090 (250W-capped) and vLLM v0.30.0; llama-benchy measures ~5993 tok/s prefill and ~199 tok/s generation.
A Framework 13 with a Ryzen 7 7840U and 64GB of unified memory runs privacy-first coding and homelab work through llama.cpp and hermes, where the larger model is too slow to use interactively.
Two single-GPU Ubuntu servers, one with a blower-modded Tesla V100 32GB and one with an RTX 3090, run Strata with Qwen 3.8 Flash Next at 262K context for local business management automation.
A Radeon 7900XTX with 24GB VRAM and 64GB DDR5 runs Qwen 3.8 Flash Next through Strata at about 60 tok/s up to 250k context while leaving VRAM for gaming.
A llama.cpp expert-streaming build runs the 177B Qwen 3.8 Flash Next MoE at roughly 11.5 tok/s on a 12GB RTX 5070 and 32GB DDR4-2400 by streaming experts from SSD.
TensorSharp runs the 176B Qwen 3.8 Flash Next MoE on a 16GB RTX 3080 Laptop with 32GB RAM, matching Strata on decode while finishing the benchmark process far faster.
Long-context decode benchmark of Qwen 3.8 Flash Next on an M1 Max 64 GB through an unofficial Splash/ds4 fork in real OpenCode agent sessions.
Four quants of a vision model measured on a 12GB RTX 5070 SFF with 64GB DDR5, through a purpose-built inference engine, at 37 to 55 GB combined RAM+VRAM.
Daily OCR of math- and table-heavy PDFs into LaTeX-correct Markdown and Word, using Qwen vision models on llama.cpp instead of a smaller model that misreads numbers.
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 self-built server with 1TB of ECC RAM and a mix of used 3090s and P100s produced internal tools whose economic impact is reported at ten times the hardware cost.
A laptop workflow combines Qwen Flash Next, llama.cpp and a DeepSeek harness, using system memory and SSD-backed loading to make a MoE model practical on 12GB of VRAM.
