HARDWARE / UNIFIED MEMORY

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.

1차 출처

Radeon 8060S compact desktop128 GB

01 / PRACTICAL CEILING

Qwen3.8 Flash Next

The highest listed result may be a tight or offloaded fit. For daily use, prefer the first result marked 여유 있음 and keep context modest.

02 / DEFAULT RUNTIME

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.

가이드 열기

03 / MODEL ENVELOPE

대표 오픈 웨이트 모델

Alibaba Qwen

Qwen3.8 Flash Next

English

180BQ4 estimated budget

추정 메모리: ~108 GB
컨텍스트: 262,144 native; 1M extended

inclusionAI

Ling-3.0-flash

English

124BQ4 estimated budget

추정 메모리: ~74.4 GB
컨텍스트: Check selected runtime and checkpoint

OpenAI

gpt-oss-120b

117B5.1B active · MXFP4

추정 메모리: ~80 GB
컨텍스트: 128K

Llama 4 Scout

109B17B active · INT4 MoE

추정 메모리: ~78 GB
컨텍스트: 10M advertised

Llama 3.1 70B

70BGGUF Q4

추정 메모리: ~46 GB
컨텍스트: 128K

Nex AGI

Nex-N2.5-mini

English

35BQ4 estimated budget

추정 메모리: ~21 GB
컨텍스트: 262,144 (config max_position_embeddings)

주의

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 (빠듯함), Ling-3.0-flash (여유 있음), gpt-oss-120b (여유 있음), Llama 4 Scout (여유 있음), Llama 3.1 70B (여유 있음), Nex-N2.5-mini (여유 있음).