What can AMD Radeon RX 9070 XT run for agents?
Build: RX 9070 XT + Ryzen 7 9700X + 32GB DDR5 (Linux/ROCm)
Runs comfortably74 models
Ranked by fit for agents use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q4_K_MContext: 8,192VRAM: 11.2 GBHeadroom: 4.8 GBollama run hermes3:8b73tok/sEstimated
ollama run hermes3:8bQuant: Q8_0Context: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBollama run qwen2.5:7b48tok/sEstimated
ollama run qwen2.5:7bQuant: Q5_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 5.1 GBollama run mistral:7b74tok/sEstimated
ollama run mistral:7bQuant: Q4_K_MContext: 8,192VRAM: 11.2 GBHeadroom: 4.8 GB73tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 11.9 GBHeadroom: 4.1 GBollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M48tok/sEstimated
ollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_MQuant: Q4_K_MContext: 8,192VRAM: 11.3 GBHeadroom: 4.7 GBollama run dolphin3:8b73tok/sEstimated
ollama run dolphin3:8bQuant: Q4_K_MContext: 4,096VRAM: 8.4 GBHeadroom: 7.6 GB84tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 5.9 GB84tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 5.9 GB84tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.3 GBHeadroom: 5.7 GB84tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 5.9 GB84tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBollama run qwen3:8b73tok/sEstimated
ollama run qwen3:8bRuns with tradeoffs98 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 2,048VRAM: 13.1 GBHeadroom: 2.9 GB- • Tight VRAM fit — only 2.9 GB headroom left for context growth
ollama run qwen2.5:14b42tok/sEstimated
- • Tight VRAM fit — only 2.9 GB headroom left for context growth
ollama run qwen2.5:14bQuant: Q4_K_MContext: 8,192VRAM: 12.4 GBHeadroom: 3.6 GB- • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run ornith:9b65tok/sEstimated
- • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run ornith:9bQuant: Q8_0Context: 8,192VRAM: 12.0 GBHeadroom: 4.0 GB- • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run llama3.1:8b42tok/sEstimated
- • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run llama3.1:8bQuant: Q4_K_MContext: 8,192VRAM: 28.7 GBHeadroom: 6.5 GB- • Partial CPU offload: ~44% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run dolphin-mistral:24b4tok/sEstimated
- • Partial CPU offload: ~44% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run dolphin-mistral:24bQuant: Q4_K_MContext: 2,048VRAM: 24.7 GBHeadroom: 10.5 GB- • Partial CPU offload: ~35% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:30b4tok/sEstimated
- • Partial CPU offload: ~35% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:30bQuant: Q4_K_MContext: 8,192VRAM: 24.1 GBHeadroom: 11.1 GB- • Partial CPU offload: ~34% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen2.5-coder:32b4tok/sEstimated
- • Partial CPU offload: ~34% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen2.5-coder:32bQuant: Q4_K_MContext: 2,048VRAM: 25.7 GBHeadroom: 9.5 GB- • Partial CPU offload: ~38% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3-coder:30b4tok/sEstimated
- • Partial CPU offload: ~38% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3-coder:30bQuant: Q4_K_MContext: 2,048VRAM: 26.0 GBHeadroom: 9.2 GB- • Partial CPU offload: ~38% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:32b3tok/sEstimated
- • Partial CPU offload: ~38% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:32bWhat if you upgraded?
Hypothetical scenarios. We re-ran the compatibility engine for each.
+32 GB system RAM
~$80–150
Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.
Unlocks: 64 new comfortable, 116 new tradeoff
- • Qwen 3 0.6B
- • Llama 3.2 3B Instruct
- • Qwen 3 1.7B
- • Gemma 3 270M
Upgrade to AMD Radeon RX 7900 XT
~$729
20 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~644 GB/s to ~800 GB/s.
Unlocks: 86 new comfortable
- • Qwen 3 0.6B
- • Llama 3.1 8B Instruct
- • Gemma 4 12B
- • Qwen3.5 9B
Add a second AMD Radeon RX 9070 XT
~$649
Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.
Unlocks: 141 new comfortable
- • Qwen 3 0.6B
- • Llama 3.1 8B Instruct
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
Won't runtop 5 popular models
Need more memory than you have. Shown for orientation.
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
How to read these numbers
Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.