Is it worth running Qwen 3.8 Flash Next on 4x3090 vs 27B?
Summary
A user is asking for advice on whether running the Qwen 3.8 Flash Next model on multiple GPUs would be better than using a larger 27B model due to performance issues and indecisiveness.
Similar Articles
I don't get the qwen 3.8 flash next hype
A community member reports that Qwen 3.8 Flash Next (UD-Q4_K_XL on 4x RTX 3090s) underperforms the Qwen 3.8 27B Q8 in a Tetris-building coding task, producing bugs and failing to deliver a playable .exe in Strata despite faster generation speeds, challenging the hype around the smaller model.
2×RTX 3090 + EPYC box running qwen3.8-flash-next at ~38 tok/s
The user describes a hardware configuration with dual RTX 3090 GPUs and an AMD EPYC CPU for running the Qwen3-Flash-Next model using llama.cpp, achieving 38 tokens per second in single-stream inference, and seeks advice on whether to add a third GPU or upgrade the CPU to improve performance, especially for running multiple parallel agents.
Anyone running qwen 3.8 27b on 5070ti (16GB)?
A user asks if running the Qwen 3.8 27b model on a 5070ti GPU with 16GB VRAM is feasible using quantization for agentic coding purposes.
Qwen3.8-Flash-Next (5.05bpw + ngram at bf16) exl3 on one r9700: 863 t/s prefill and 35 t/s decode at 230k context (256k max), is that ok or am i missing something?
A user shares and asks for feedback on running Qwen3.8-Flash-Next in EXL3 5.05bpw on a single Radeon RX 9700 (gfx12) with mixed GPU/CPU expert offloading, reporting ~863 t/s prefill and ~35 t/s decode at 230k context.
Qwen3.8-27B vs Qwen3.8-Flash-Next smaller quant?
A user compares Qwen3.8-27B and Qwen3.8-Flash-Next models for intelligence and coding performance with 128GB RAM, seeking advice on which is better.