Qwen3.8-Flash-Next

Running Qwen3.8-Flash-Next locally

At Q4_K_M and 4K of context, Qwen3.8-Flash-Next needs about 79.3 GB — 72.0 GB of weights, 0.12 GB of KV cache and a 7.2 GB activation buffer. The smallest cards in this index that clear that comfortably are 128 GB ones — 4 of them, from the DGX Spark 128G up — and 8 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 0.82 GB, taking the total to 80.2 GB. That is gentler than the parameter count suggests: only 12 of 48 layers keep a KV cache that grows with context, so the cache scales at a fraction of the usual rate. The model's native window is 256K; holding all of it at Q4_K_M would need about 87 GB.

Which build to download

This index only tracks Qwen3.8-Flash-Next in GGUF, across 2 levels (Q4_K_M, Q8_0). No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.

Common questions

How much VRAM does Qwen3.8-Flash-Next need?

About 79.3 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 80.2 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.

Will Qwen3.8-Flash-Next run on a 128GB GPU?

Yes — at Q4_K_M and 4K context it needs about 79.3 GB, which leaves 48.7 GB spare on a DGX Spark 128G, or on any of the other 128 GB cards here (4 in all). That is the smallest size in this index that clears it comfortably; 8 of 78 do.

Which quantization of Qwen3.8-Flash-Next should I use?

No published quality comparison exists for this model, so pick by footprint: Q4_K_M is the level most people run, and a higher bits-per-weight level is more faithful. All 2 levels in the index are Q4_K_M, Q8_0. Note this is a mixture-of-experts model — all parameters must be resident even though only a fraction are active per token, so the memory cost follows the total, not the active count.