How much memory does Qwen3.8 Flash Next need?
About 111 GB at Q4_K_M with an 8K context. It runs on a Mac with 192 GB of unified memory or more.
Try other settings in the calculatorMemory by quantization and context
Total memory: weights, KV cache in F16 and about 1 GB of buffers. Under each total, the smallest Mac that can run it with the default GPU memory limit.
| Quantization | 8K context | 32K context | 128K context |
|---|---|---|---|
| Q3_K_M | 89 GB128 GB Mac | 90 GB128 GB Mac | 92 GB128 GB Mac |
| Q4_K_M | 111 GB192 GB Mac | 112 GB192 GB Mac | 114 GB192 GB Mac |
| Q5_K_M | 129 GB192 GB Mac | 130 GB192 GB Mac | 132 GB192 GB Mac |
| Q6_K | 149 GB256 GB Mac | 149 GB256 GB Mac | 152 GB256 GB Mac |
| Q8_0 | 192 GBtoo big for a Mac | 193 GBtoo big for a Mac | 195 GBtoo big for a Mac |
| F16 | 361 GBtoo big for a Mac | 362 GBtoo big for a Mac | 364 GBtoo big for a Mac |
About the model
- Parameters
- 180B
- Type
- Mixture of experts, 512 experts
- Attention
- hybrid: linear attention plus full attention
- KV cache, F16
- 0.2 GB at 8K, 3.2 GB at 128K
- On Hugging Face
- Qwen/Qwen3.8-Flash-Next
Most layers use linear attention, which keeps a small fixed-size state instead of a cache. Only the full-attention layers grow with context, so long contexts are cheap. As a mixture-of-experts model it loads every expert into memory, so memory follows the total parameter count, while speed follows the smaller number of active parameters.
Questions
How much memory does Qwen3.8 Flash Next need?
About 111 GB at Q4_K_M with an 8K context: 110 GB of weights, 0.2 GB of KV cache and about 1 GB of buffers. At 32K context it needs about 112 GB.
Can Qwen3.8 Flash Next run on a Mac?
Yes. At Q4_K_M with an 8K context it fits on a Mac with 192 GB of unified memory or more, using the default GPU memory limit of about three quarters.
How big is the Qwen3.8 Flash Next KV cache?
About 0.2 GB at 8K tokens and 3.2 GB at 128K tokens with an F16 cache. Its attention design: hybrid: linear attention plus full attention.
Other models
- Gemma 4 12B
- gpt-oss 20B
- Gemma 4 26B-A4B
- Qwen3.8 27B
- GLM-4.7 Flash
- Gemma 4 31B
- Qwen3.6 35B-A3B
- gpt-oss 120B
- Mistral Medium 3.5
- DeepSeek V4 Flash
- GLM-5.3
- DeepSeek V4 Pro
- Kimi K3
Data read from Hugging Face on 2026-11-09. These are estimates; benchmarks on this site report measured memory. How the estimate works. Compare all models in the model fit chart.
Get the next one
New benchmarks and agent runs by email, with the raw data. Or follow on RSS or X.