Model · Alibaba Qwen

Qwen3.8 Flash-Next

180B MoE · Q4_K · 103.7 GB · open weights · curated for general, coding, agents · repo created 2026-08-24

Too much for a 24 GB card: 107.8 GB at 8K context against 21.1 GB usable. Barely fits NVIDIA DGX Spark.

What the model needs: weights, context cache and runtime overhead at four reference contexts. The total is the model's own; what differs per machine is the usable memory it has to fit into — VRAM on a graphics card, unified memory on a Mac.

Cache shape from the model's config: 12 of 48 layers cache the full context, each storing K and V for 2 KV heads × 256 dimensions per token at f16; 36 layers keep a constant-size state that does not grow with context. Multiply those four numbers by two bytes and by the context length and you have the cache column.

All memory figures are estimates: measured quantized file size + computed context memory + runtime overhead, with a 12% safety margin on your hardware. Real usage varies with runtime version and settings.

Every tracked GPU and Mac at 8K and 32K context with a full-precision (f16) cache — the same engine as the finder and the GPU pages.

Runs on 0 of 32 tracked devices at 8K context, easily or with ordinary headroom.

GGUF is the quantized single-file format local runtimes load (Ollama, LM Studio, llama.cpp); our memory figures are measured from the linked GGUF file. The original repo holds full-precision safetensors — a much larger download meant for GPUs with far more memory.

More from Alibaba Qwen

• Qwen3.8 27Babout the same ◆
• Qwen3.8 2.4T-A95Bmore popular ▲
• Qwen3 14Babout the same ◆
• Qwen3-Coder Nextmore popular ▲
• Qwen3 0.6Bfading ▼
• Qwen3-Coder 30B-A3Babout the same ◆

Every tracked model →