AMD graphics card
What AI models can the AMD Radeon RX 9060 XT 16 GB run?
At 4-bit quantization with an 8K-token conversation, 28 of the 146 open-weight models in our directory fit entirely in the AMD Radeon RX 9060 XT 16 GB's 16 GB of video memory (about 15 GB usable), up to Safety GPT OSS 20B. With 32 GB of dual-channel DDR5-5600, 33 more run partly from system RAM, more slowly. Among models of 7B parameters or more, GPT OSS 20B is the fastest, at an estimated 54 to 70 tokens per second.
| Model | Parameters | Memory needed | Estimated speed |
|---|---|---|---|
| Runs entirely in fast memory (28) | |||
| Safety GPT OSS 20B OpenAI | 21.5B 4.8B active | 14 GB 13 GB + 0.2 GB cache | 48–63 tokens/s Fast |
| GPT OSS 20B OpenAI | 20.9B 4.2B active | 14 GB 13 GB + 0.2 GB cache | 54–70 tokens/s Fast |
| Reka Flash 3 Rekaai | 20.9B | 15 GB 13 GB + 1.1 GB cache | 16–21 tokens/s Comfortable to read, little memory to spare |
| Qwen3 14B Alibaba (Qwen) | 14.8B | 11 GB 9.0 GB + 1.3 GB cache | 22–29 tokens/s Comfortable to read |
| Phi 4 Microsoft | 14.7B | 11 GB 8.9 GB + 1.7 GB cache | 22–28 tokens/s Comfortable to read |
| Ministral 3 14B Mistral AI | 13.9B | 11 GB 8.5 GB + 1.3 GB cache | 23–30 tokens/s Comfortable to read |
| Gemma 3 12B IT Google DeepMind | 12.2B | 8.2 GB weights only | Speed not estimated (architecture not public) |
| Llama Guard 4 12B Meta | 12.0B | 8.1 GB weights only | Speed not estimated (architecture not public) |
| Qwen3.5 9B Alibaba (Qwen) | 9.7B | 6.9 GB 5.9 GB + 0.3 GB cache | 35–45 tokens/s Fast |
| Moondream 3.1 Moondream | 9.3B | 6.4 GB weights only | Speed not estimated (architecture not public) |
| Moondream 3 Preview Moondream | 9.3B | 6.4 GB weights only | Speed not estimated (architecture not public) |
| Ministral 3 8B Mistral AI | 8.9B | 7.3 GB 5.4 GB + 1.1 GB cache | 35–46 tokens/s Fast |
| Granite 4.2 8B IBM | 8.8B | 7.5 GB 5.3 GB + 1.3 GB cache | 35–45 tokens/s Fast |
| Qwen3 VL 8B Instruct Alibaba (Qwen) | 8.8B | 7.3 GB 5.3 GB + 1.2 GB cache | 35–46 tokens/s Fast |
| Qwen3 VL 8B Thinking Alibaba (Qwen) | 8.8B | 7.3 GB 5.3 GB + 1.2 GB cache | 35–46 tokens/s Fast |
| UI-TARS 7B Bytedance | 8.3B | 6.3 GB 5.0 GB + 0.5 GB cache | 40–51 tokens/s Fast |
| Qwen3 8B Alibaba (Qwen) | 8.2B | 7.0 GB 5.0 GB + 1.2 GB cache | 38–49 tokens/s Fast |
| Llama 3.1 8B Instruct fp8 Meta | 8.0B | 5.7 GB weights only | Speed not estimated (architecture not public) |
| Hy-MT2-7B Tencent (Hunyuan) | 8.0B | 6.7 GB 4.9 GB + 1.1 GB cache | 39–50 tokens/s Fast |
| Qwen2.5 7B Instruct Alibaba (Qwen) | 7.6B | 5.9 GB 4.6 GB + 0.5 GB cache | 43–55 tokens/s Fast |
| Gemma 3 4B IT Google DeepMind | 4.3B | 3.4 GB weights only | Speed not estimated (architecture not public) |
| Nemotron 3.5 Content Safety (free) NVIDIA | 4.3B | 3.7 GB 2.6 GB + 0.3 GB cache | 72–94 tokens/s Fast |
| Ministral 3 3B Mistral AI | 3.8B | 4.0 GB 2.3 GB + 0.9 GB cache | 72–93 tokens/s Fast |
| Llama 3.2 3B Instruct Meta | 3.2B | 2.7 GB weights only | Speed not estimated (architecture not public) |
| Granite 4.0 Micro IBM | 3.2B | 2.8 GB 1.9 GB + 0.1 GB cache | 98–126 tokens/s Fast |
| Hy-MT2-1.8B Tencent (Hunyuan) | 2.0B | 2.6 GB 1.2 GB + 0.5 GB cache | 123–159 tokens/s Fast |
| Hy-MT2-1.8B Tencent (Hunyuan) | 2.0B | 2.6 GB 1.2 GB + 0.5 GB cache | 123–159 tokens/s Fast |
| Llama 3.2 1B Instruct Meta | 1.2B | 1.5 GB weights only | Speed not estimated (architecture not public) |
| Runs, partly from system RAM (slower) (33) | |||
| Skyfall 36B V2 Thedrummer | 36.9B | 25 GB 22 GB + 2.1 GB cache | 2.3–3.2 tokens/s Too slow for chat, 9.9 GB in system RAM |
| Qwen3.5 35B-A3B Alibaba (Qwen) | 36.0B 4.7B active | 23 GB 22 GB + 0.2 GB cache | 27–38 tokens/s Fast, 7.4 GB in system RAM |
| Qwen3.6 35B-A3B Alibaba (Qwen) | 36.0B 4.7B active | 23 GB 22 GB + 0.2 GB cache | 27–38 tokens/s Fast, 7.4 GB in system RAM |
| Nex-N2.5-Mini NEX AGI | 35.1B 3.9B active | 22 GB 21 GB + 0.2 GB cache | 32–44 tokens/s Fast, 6.9 GB in system RAM |
| Laguna XS 2.1 (free) Poolside | 33.4B 2.2B active | 21 GB 20 GB + 0.4 GB cache | 43–60 tokens/s Fast, 6.1 GB in system RAM |
| Qwen3 VL 32B Instruct Alibaba (Qwen) | 33.4B | 23 GB 20 GB + 2.1 GB cache | 2.8–3.9 tokens/s Too slow for chat, 7.8 GB in system RAM |
| Qwen2.5 Coder 32B Instruct Alibaba (Qwen) | 32.8B | 23 GB 20 GB + 2.1 GB cache | 2.9–4.0 tokens/s Too slow for chat, 7.4 GB in system RAM |
| Qwen3 32B Alibaba (Qwen) | 32.8B | 23 GB 20 GB + 2.1 GB cache | 2.9–4.0 tokens/s Too slow for chat, 7.4 GB in system RAM |
| Nemotron 3 Nano 30B A3B NVIDIA | 31.6B | 20 GB 19 GB + 0.1 GB cache | 4.6 GB in system RAM; Speed not estimated for this architecture |
| Nemotron 3.5 Lightning 30B A3B NVIDIA | 31.6B | 20 GB 19 GB + 0.4 GB cache | 5.0 GB in system RAM; Speed not estimated for this architecture |
| Gemma 4 31B IT Google DeepMind | 31.3B | 22 GB 19 GB + 2.2 GB cache | 3.2–4.4 tokens/s Too slow for chat, 6.5 GB in system RAM |
| GLM-4.7-Flash Zhipu AI (Z.ai) | 31.2B 5.2B active | 20 GB 19 GB + 0.4 GB cache | 24–32 tokens/s Comfortable to read, 4.8 GB in system RAM |
| Qwen3 VL 30B A3B Instruct Alibaba (Qwen) | 31.1B 3.9B active | 20 GB 19 GB + 0.8 GB cache | 26–36 tokens/s Fast, 5.0 GB in system RAM |
| Qwen3 VL 30B A3B Thinking Alibaba (Qwen) | 31.1B 3.9B active | 20 GB 19 GB + 0.8 GB cache | 26–36 tokens/s Fast, 5.0 GB in system RAM |
| Qwen3-Coder 30B-A3B Instruct Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 29–40 tokens/s Fast, 4.7 GB in system RAM |
| Qwen3 30B A3B Instruct 2507 Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 29–40 tokens/s Fast, 4.7 GB in system RAM |
| Qwen3 30B A3B Thinking 2507 Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 29–40 tokens/s Fast, 4.7 GB in system RAM |
| Qwen3 30B A3B Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 29–40 tokens/s Fast, 4.7 GB in system RAM |
| Hy-MT2-30B-A3B Tencent (Hunyuan) | 30.1B 3.5B active | 20 GB 18 GB + 0.8 GB cache | 29–40 tokens/s Fast, 4.4 GB in system RAM |
| Muse Glimmer 30B Meta | 29.8B | 19 GB 18 GB + 0.2 GB cache | 4.6–6.3 tokens/s Usable but slow, 3.6 GB in system RAM |
| Qwen3.8 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 5.4–7.4 tokens/s Usable but slow, 2.8 GB in system RAM |
| Qwen3.5 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 5.4–7.4 tokens/s Usable but slow, 2.8 GB in system RAM |
| Qwen3.6 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 5.4–7.4 tokens/s Usable but slow, 2.8 GB in system RAM |
| Gemma 3 27B IT Google DeepMind | 27.4B | 17 GB weights only | 2.0 GB in system RAM; Speed not estimated (architecture not public) |
| Gemma 2 27B Google DeepMind | 27.2B | 17 GB weights only | 1.9 GB in system RAM; Speed not estimated (architecture not public) |
| Gemma 4 26B A4B IT Google DeepMind | 25.8B | 17 GB 16 GB + 0.5 GB cache | 1.6 GB in system RAM; Speed not estimated for this architecture |
| Voxtral Small 24B 2507 Mistral AI | 24.3B | 17 GB 15 GB + 1.3 GB cache | 7.3–10 tokens/s Usable but slow, 1.5 GB in system RAM |
| Uncensored Cognitivecomputations | 24.0B | 17 GB 15 GB + 1.3 GB cache | 7.6–10 tokens/s Usable but slow, 1.3 GB in system RAM |
| Mistral Small 3.1 24B Instruct Mistral AI | 24.0B | 17 GB 15 GB + 1.3 GB cache | 7.6–10 tokens/s Usable but slow, 1.3 GB in system RAM |
| LFM2.5-24B-A2B Liquid | 24.0B | 16 GB 15 GB + 0.2 GB cache | 0.1 GB in system RAM; Speed not estimated for this architecture |
| Mistral Small 3 Mistral AI | 23.6B | 16 GB 14 GB + 1.3 GB cache | 8.2–11 tokens/s Usable but slow, 1.0 GB in system RAM |
| Cydonia 24B V4.1 Thedrummer | 23.6B | 16 GB 14 GB + 1.3 GB cache | 8.2–11 tokens/s Usable but slow, 1.0 GB in system RAM |
| Cydonia 24B V4.1 Thedrummer | 23.6B | 16 GB 14 GB + 1.3 GB cache | 8.2–11 tokens/s Usable but slow, 1.0 GB in system RAM |
85 larger models do not fit. Change the quantization, conversation length or system RAM in the tool.
Compared with similar cards
- NVIDIA GeForce RTX 5070 12 GB: 12 GB, 25 models fit entirely (-3); about 121% faster on models that fit both (672 vs 320 GB/s, and AMD cards run llama.cpp less efficiently than NVIDIA's).
- NVIDIA GeForce RTX 5080 16 GB: same memory, so the same models fit; about 205% faster on models that fit both (960 vs 320 GB/s, and AMD cards run llama.cpp less efficiently than NVIDIA's).
- NVIDIA GeForce RTX 5070 Ti 16 GB: same memory, so the same models fit; about 187% faster on models that fit both (896 vs 320 GB/s, and AMD cards run llama.cpp less efficiently than NVIDIA's).
- NVIDIA GeForce RTX 4080 SUPER 16 GB: same memory, so the same models fit; about 141% faster on models that fit both (736 vs 320 GB/s, and AMD cards run llama.cpp less efficiently than NVIDIA's).
- NVIDIA GeForce RTX 4090 24 GB: 24 GB, 60 models fit entirely (+32); about 217% faster on models that fit both (1008 vs 320 GB/s, and AMD cards run llama.cpp less efficiently than NVIDIA's).
Frequently asked questions
What is the largest AI model the AMD Radeon RX 9060 XT 16 GB can run?
At 4-bit quantization with an 8K-token conversation, the largest model in our directory that fits entirely in its 16 GB of video memory is Safety GPT OSS 20B (14 GB). With 32 GB of dual-channel DDR5-5600 for the overflow, larger models such as Skyfall 36B V2 also run, more slowly, partly from system RAM.
Can the AMD Radeon RX 9060 XT 16 GB run GPT OSS 20B?
Yes. At 4-bit, GPT OSS 20B needs about 14 GB and fits entirely in the AMD Radeon RX 9060 XT 16 GB's memory at an estimated 54 to 70 tokens per second.
Can the AMD Radeon RX 9060 XT 16 GB run Qwen3 32B?
Partly. Qwen3 32B needs about 23 GB at 4-bit, so about 7.4 GB runs from system RAM (assuming 32 GB of dual-channel DDR5-5600) at an estimated 2.9 to 4.0 tokens per second.
Can the AMD Radeon RX 9060 XT 16 GB run OpenAI GPT 120B?
No. OpenAI GPT 120B needs about 72 GB at 4-bit, more than the AMD Radeon RX 9060 XT 16 GB can hold even with 32 GB of dual-channel DDR5-5600 for overflow.
These are estimates, not measurements: memory from each model's parameter count and published architecture, speed from memory bandwidth, calibrated on the AIPCs test bench. Drivers, software and prompt length move real results. How the estimate works.