What can AMD Radeon RX 7900 XTX run?
Build: AMD Radeon RX 7900 XTX + — + 32 GB RAM (windows)
Memory: 24 GB VRAM + 32 GB system RAM
Runner: llama.cpp (Vulkan)
Runs comfortably184 models
Full-VRAM resident, with room for context. No compromises.
Quant: Q4_K_MContext: 8,192VRAM: 1.6 GBHeadroom: 22.4 GBTTFT: instant1193tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 1.6 GBHeadroom: 22.4 GBTTFT: instant
1193
tok/s
Estimated
Weights
0.30 GB
KV cache
0.30 GB
Activations
0.02 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~13 ms (instant)
Quant: FP16Context: 8,192VRAM: 19.0 GBHeadroom: 5.0 GBTTFT: fastollama run llama3.1:8b27tok/sEstimated
Quant: FP16Context: 8,192VRAM: 19.0 GBHeadroom: 5.0 GBTTFT: fast
ollama run llama3.1:8b27
tok/s
Estimated
Weights
16.10 GB
KV cache
1.07 GB
Activations
0.81 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 13.6 GBHeadroom: 10.4 GBTTFT: fastollama run qwen3:8b51tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 13.6 GBHeadroom: 10.4 GBTTFT: fast
ollama run qwen3:8b51
tok/s
Estimated
Weights
8.20 GB
KV cache
4.00 GB
Activations
0.42 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 15.0 GBHeadroom: 9.0 GBTTFT: fastollama run gemma4:12b60tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 15.0 GBHeadroom: 9.0 GBTTFT: fast
ollama run gemma4:12b60
tok/s
Estimated
Weights
7.60 GB
KV cache
6.00 GB
Activations
0.39 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~250 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 12.4 GBHeadroom: 11.6 GBTTFT: fastollama run qwen3.5:9b80tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 12.4 GBHeadroom: 11.6 GBTTFT: fast
ollama run qwen3.5:9b80
tok/s
Estimated
Weights
6.60 GB
KV cache
4.50 GB
Activations
0.34 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~188 ms (fast)
Quant: MXFP4Context: 2,048VRAM: 18.3 GBHeadroom: 5.7 GBTTFT: fastollama run gpt-oss:20b21tok/sEstimated
Quant: MXFP4Context: 2,048VRAM: 18.3 GBHeadroom: 5.7 GBTTFT: fast
ollama run gpt-oss:20b21
tok/s
Estimated
Weights
14.00 GB
KV cache
2.61 GB
Activations
0.70 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~436 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 6.1 GBHeadroom: 17.9 GBTTFT: instantollama run llama3.2:3b136tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 6.1 GBHeadroom: 17.9 GBTTFT: instant
ollama run llama3.2:3b136
tok/s
Estimated
Weights
3.40 GB
KV cache
1.50 GB
Activations
0.18 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~63 ms (instant)
Quant: Q4_K_MContext: 8,192VRAM: 2.8 GBHeadroom: 21.2 GBTTFT: instant421tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 2.8 GBHeadroom: 21.2 GBTTFT: instant
421
tok/s
Estimated
Weights
0.90 GB
KV cache
0.85 GB
Activations
0.05 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~35 ms (instant)
Quant: Q4_K_MContext: 8,192VRAM: 16.8 GBHeadroom: 7.2 GBTTFT: fastollama run qwen3:14b51tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 16.8 GBHeadroom: 7.2 GBTTFT: fast
ollama run qwen3:14b51
tok/s
Estimated
Weights
8.40 GB
KV cache
7.00 GB
Activations
0.43 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~292 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 10.0 GBHeadroom: 14.0 GBTTFT: fastollama run qwen2.5:7b58tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 10.0 GBHeadroom: 14.0 GBTTFT: fast
ollama run qwen2.5:7b58
tok/s
Estimated
Weights
8.10 GB
KV cache
0.47 GB
Activations
0.41 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 1.3 GBHeadroom: 22.7 GBTTFT: instant2650tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 1.3 GBHeadroom: 22.7 GBTTFT: instant
2650
tok/s
Estimated
Weights
0.16 GB
KV cache
0.14 GB
Activations
0.02 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~6 ms (instant)
Quant: Q4_K_MContext: 2,048VRAM: 18.7 GBHeadroom: 5.3 GBTTFT: noticeableollama run mistral-small:24b30tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 18.7 GBHeadroom: 5.3 GBTTFT: noticeable
ollama run mistral-small:24b30
tok/s
Estimated
Weights
14.00 GB
KV cache
3.00 GB
Activations
0.70 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~500 ms (noticeable)
Runs with tradeoffs56 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 2,048VRAM: 23.7 GBHeadroom: 0.3 GBTTFT: noticeable- • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run qwen3:30b24tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 23.7 GBHeadroom: 0.3 GBTTFT: noticeable
- • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run qwen3:30b24
tok/s
Estimated
Weights
18.00 GB
KV cache
3.75 GB
Activations
0.90 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~625 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 23.1 GBHeadroom: 0.9 GBTTFT: noticeable- • Tight VRAM fit — only 0.9 GB headroom left for context growth
ollama run qwen2.5-coder:32b22tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 23.1 GBHeadroom: 0.9 GBTTFT: noticeable
- • Tight VRAM fit — only 0.9 GB headroom left for context growth
ollama run qwen2.5-coder:32b22
tok/s
Estimated
Weights
19.00 GB
KV cache
2.15 GB
Activations
0.96 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 22.2 GBHeadroom: 1.8 GBTTFT: noticeable- • Tight VRAM fit — only 1.8 GB headroom left for context growth
ollama run qwen3.6:27b27tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 22.2 GBHeadroom: 1.8 GBTTFT: noticeable
- • Tight VRAM fit — only 1.8 GB headroom left for context growth
ollama run qwen3.6:27b27
tok/s
Estimated
Weights
17.00 GB
KV cache
3.38 GB
Activations
0.85 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~563 ms (noticeable)
Quant: Q5_K_MContext: 8,192VRAM: 40.1 GBHeadroom: 3.1 GBTTFT: noticeable- • Partial CPU offload: ~40% of layers run on CPU
ollama run qwen3:32b20tok/sEstimated
Quant: Q5_K_MContext: 8,192VRAM: 40.1 GBHeadroom: 3.1 GBTTFT: noticeable
- • Partial CPU offload: ~40% of layers run on CPU
ollama run qwen3:32b20
tok/s
Estimated
Weights
22.00 GB
KV cache
16.00 GB
Activations
1.11 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 23.8 GBHeadroom: 0.2 GBTTFT: noticeable- • Tight VRAM fit — only 0.2 GB headroom left for context growth
ollama run gemma4:31b23tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 23.8 GBHeadroom: 0.2 GBTTFT: noticeable
- • Tight VRAM fit — only 0.2 GB headroom left for context growth
ollama run gemma4:31b23
tok/s
Estimated
Weights
18.00 GB
KV cache
3.88 GB
Activations
0.90 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~646 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 36.0 GBHeadroom: 7.2 GBTTFT: noticeable- • Partial CPU offload: ~33% of layers run on CPU
ollama run qwen3-coder:30b24tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 36.0 GBHeadroom: 7.2 GBTTFT: noticeable
- • Partial CPU offload: ~33% of layers run on CPU
ollama run qwen3-coder:30b24
tok/s
Estimated
Weights
19.00 GB
KV cache
15.00 GB
Activations
0.96 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~625 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 37.0 GBHeadroom: 6.2 GBTTFT: noticeable- • Partial CPU offload: ~35% of layers run on CPU
ollama run deepseek-r1:32b22tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 37.0 GBHeadroom: 6.2 GBTTFT: noticeable
- • Partial CPU offload: ~35% of layers run on CPU
ollama run deepseek-r1:32b22
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 30.6 GBHeadroom: 12.6 GBTTFT: noticeable- • Partial CPU offload: ~22% of layers run on CPU
ollama run qwen3.6:35b-a3b20tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 30.6 GBHeadroom: 12.6 GBTTFT: noticeable
- • Partial CPU offload: ~22% of layers run on CPU
ollama run qwen3.6:35b-a3b20
tok/s
Estimated
Weights
24.00 GB
KV cache
4.38 GB
Activations
1.20 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~730 ms (noticeable)
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: 73 new tradeoff
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen3.6 27B
- • Llama 3.3 70B Instruct
Upgrade to AMD Instinct MI210
see current pricing
64 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~960 GB/s to ~1638 GB/s.
Unlocks: 71 new comfortable
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen3.6 27B
- • Llama 3.3 70B Instruct
Add a second AMD Radeon RX 7900 XTX
~$899
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: 53 new comfortable
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen3.6 27B
- • Qwen 3 32B
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 (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
How to read these numbers
Measured here
Measured here - RunLocalAI ran this exact combo on owner hardware with public evidence.Source-backed
Source-backed / community - a reproduced public source supports the speed, but it is not labeled as owner-measured.Extrapolated
Extrapolated - predicted from a measured benchmark on similar-bandwidth hardware.Estimated
Estimated - formula based on VRAM bandwidth and model architecture; not a benchmark row.Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.