Framework Desktop · Ryzen AI Max+ 395 · 128 GB
A 128 GB Strix Halo desktop. AMD allows a large graphics-memory allocation, but usable capacity and speed depend on BIOS, driver, and runtime support.
Primary sourceQwen3.8 Flash Next
The highest listed result may be a tight or offloaded fit. For daily use, prefer the first result marked Comfortable and keep context modest.
llama.cpp
GGUF models, CPU/GPU offload, embedded and unusual hardware. New architectures may require a recent build. Backend availability does not imply equal performance. Since v0.7.0 (2026-10-15) llama-server listens on port 9931 by default instead of 8080; the example commands pin that port explicitly. Older builds accept the same --port flag but default to 8080.
Open guideRepresentative open-weight models
Qwen3.8 Flash Next
- Estimated memory
- ~108 GB
- Context
- 262,144 native; 1M extended
Ling-3.0-flash
- Estimated memory
- ~74.4 GB
- Context
- Check selected runtime and checkpoint
gpt-oss-120b
- Estimated memory
- ~80 GB
- Context
- 128K
Llama 4 Scout
- Estimated memory
- ~78 GB
- Context
- 10M advertised
Llama 3.1 70B
- Estimated memory
- ~46 GB
- Context
- 128K
Nex-N2.5-mini
- Estimated memory
- ~21 GB
- Context
- 262,144 (config max_position_embeddings)
Fit is based on estimated total model memory. Driver support, KV cache, multimodal projectors, concurrency, and desktop applications can all reduce available headroom. Current fit: Qwen3.8 Flash Next (Tight fit), Ling-3.0-flash (Comfortable), gpt-oss-120b (Comfortable), Llama 4 Scout (Comfortable), Llama 3.1 70B (Comfortable), Nex-N2.5-mini (Comfortable).