HARDWARE / VRAM

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.

Fonte primaria

RDNA 4 workstation GPU32 GB

01 / PRACTICAL CEILING

Qwen3.6 35B-A3B

The highest listed result may be a tight or offloaded fit. For daily use, prefer the first result marked Comfortable 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.

Apri guida

03 / MODEL ENVELOPE

Modelli open-weight rappresentativi

Alibaba Qwen

Qwen3.6 35B-A3B

35B3B active · Q4 / NVFP4 MoE

Memoria stimata: ~25 GB
Contesto: 262K native

Alibaba Qwen

Qwen3 32B

32BGGUF Q4

Memoria stimata: ~24.5 GB
Contesto: 32K+

Alibaba Qwen

Qwen3 30B-A3B

30B3B active · GGUF Q4 MoE

Memoria stimata: ~22.5 GB
Contesto: 32K+

Alibaba Qwen

Qwen3.6 27B

27BQ4 / NVFP4 estimate

Memoria stimata: ~18.5 GB
Contesto: 262K native

Alibaba Qwen

Qwen3.8 27B

27BQ4 estimate

Memoria stimata: ~19.5 GB
Contesto: 262K native

Google

Gemma 3 27B

27BINT4

Memoria stimata: ~20.5 GB
Contesto: 128K

Attenzione

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: Qwen3.6 35B-A3B (Tight), Qwen3 32B (Tight), Qwen3 30B-A3B (Tight), Qwen3.6 27B (Comfortable), Qwen3.8 27B (Comfortable), Gemma 3 27B (Comfortable).