Radeon AI PRO R9700 · 32 GB
A 32 GB AMD workstation card for larger single-GPU quantized models. Check the exact operating-system and ROCm or Vulkan runtime path first.
Source primaireNex-N2.5-mini
The highest listed result may be a tight or offloaded fit. For daily use, prefer the first result marked Confortable 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.
Ouvrir le guideModèles open-weight représentatifs
Nex-N2.5-mini
English- Mémoire estimée
- ~21 GB
- Contexte
- 262,144 (config max_position_embeddings)
Qwen3.6 35B-A3B
- Mémoire estimée
- ~25 GB
- Contexte
- 262K native
Qwen3 32B
- Mémoire estimée
- ~24.5 GB
- Contexte
- 32K+
Qwen3 30B-A3B
- Mémoire estimée
- ~22.5 GB
- Contexte
- 32K+
Qwen3.6 27B
- Mémoire estimée
- ~18.5 GB
- Contexte
- 262K native
Qwen3.8 27B
- Mémoire estimée
- ~19.5 GB
- Contexte
- 262K native
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: Nex-N2.5-mini (Confortable), Qwen3.6 35B-A3B (Serré), Qwen3 32B (Serré), Qwen3 30B-A3B (Serré), Qwen3.6 27B (Confortable), Qwen3.8 27B (Confortable).