What can AMD Radeon RX 9070 XT run for reasoning?
Build: AMD Radeon RX 9070 XT + — + 32 GB RAM (windows)
Runs comfortably90 models
Ranked by fit for reasoning use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q4_K_MContext: 8,192VRAM: 9.4 GBHeadroom: 6.6 GBollama run deepseek-r1:7b69tok/sEstimated
ollama run deepseek-r1:7bQuant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 5.8 GB60tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 5.8 GBollama run RefinedNeuro/RN_TR_R1:latest60tok/sEstimated
ollama run RefinedNeuro/RN_TR_R1:latestQuant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GB60tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 5.2 GB53tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 11.6 GBHeadroom: 4.4 GBollama run phi4-reasoning:14b34tok/sEstimated
ollama run phi4-reasoning:14bQuant: Q4_K_MContext: 2,048VRAM: 11.6 GBHeadroom: 4.4 GBollama run deepseek-r1:14b34tok/sEstimated
ollama run deepseek-r1:14bQuant: Q4_K_MContext: 8,192VRAM: 9.1 GBHeadroom: 6.9 GB69tok/sEstimated
Quant: Q4_K_MContext: 4,096VRAM: 7.4 GBHeadroom: 8.6 GB69tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 9.1 GBHeadroom: 6.9 GB69tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 9.4 GBHeadroom: 6.6 GB62tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 11.6 GBHeadroom: 4.4 GBollama run phi4:14b34tok/sEstimated
ollama run phi4:14bRuns with tradeoffs83 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 2,048VRAM: 13.0 GBHeadroom: 3.0 GB- • Tight VRAM fit — only 3.0 GB headroom left for context growth
200tok/sEstimated
- • Tight VRAM fit — only 3.0 GB headroom left for context growth
Quant: Q4_K_MContext: 8,192VRAM: 27.7 GBHeadroom: 7.5 GB- • Partial CPU offload: ~42% of layers run on CPU
20tok/sEstimated
- • Partial CPU offload: ~42% of layers run on CPU
Quant: Q4_K_MContext: 8,192VRAM: 34.5 GBHeadroom: 0.7 GB- • Partial CPU offload: ~54% of layers run on CPU
15tok/sEstimated
- • Partial CPU offload: ~54% of layers run on CPU
Quant: Q4_K_MContext: 2,048VRAM: 25.0 GBHeadroom: 10.2 GB- • Partial CPU offload: ~36% of layers run on CPU
ollama run deepseek-r1:32b15tok/sEstimated
- • Partial CPU offload: ~36% of layers run on CPU
ollama run deepseek-r1:32bQuant: Q4_K_MContext: 2,048VRAM: 25.0 GBHeadroom: 10.2 GB- • Partial CPU offload: ~36% of layers run on CPU
ollama run qwq:32b15tok/sEstimated
- • Partial CPU offload: ~36% of layers run on CPU
ollama run qwq:32bQuant: Q4_K_MContext: 2,048VRAM: 23.5 GBHeadroom: 11.7 GB- • Partial CPU offload: ~32% of layers run on CPU
15tok/sEstimated
- • Partial CPU offload: ~32% of layers run on CPU
Quant: Q4_K_MContext: 2,048VRAM: 23.5 GBHeadroom: 11.7 GB- • Partial CPU offload: ~32% of layers run on CPU
15tok/sEstimated
- • Partial CPU offload: ~32% of layers run on CPU
Quant: AWQ-INT4Context: 2,048VRAM: 25.0 GBHeadroom: 10.2 GB- • Partial CPU offload: ~36% of layers run on CPU
9tok/sEstimated
- • Partial CPU offload: ~36% of layers run on CPU
What 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, 102 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: 79 new comfortable
- • Qwen 3 0.6B
- • Gemma 4 12B
- • Qwen3.5 9B
- • Llama 3.2 3B Instruct
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: 135 new comfortable
- • Qwen 3 0.6B
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen3.6 27B
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.