What can AMD Radeon RX 7900 XTX run?
Build: RX 7900 XTX + Ryzen 9 7950X + 64GB DDR5 (Linux/ROCm)
Memory: 24 GB VRAM + 64 GB system RAM
Runner: llama.cpp (ROCm)
Runs comfortably183 models
Full-VRAM resident, with room for context. No compromises.
Quant: Q4_K_MContext: 8,192VRAM: 2.6 GBHeadroom: 21.4 GBTTFT: instant1458tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 2.6 GBHeadroom: 21.4 GBTTFT: instant
1458
tok/s
Estimated
Weights
0.30 GB
KV cache
0.30 GB
Activations
0.02 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~13 ms (instant)
Quant: FP16Context: 8,192VRAM: 20.0 GBHeadroom: 4.0 GBTTFT: fastollama run llama3.1:8b33tok/sEstimated
Quant: FP16Context: 8,192VRAM: 20.0 GBHeadroom: 4.0 GBTTFT: fast
ollama run llama3.1:8b33
tok/s
Estimated
Weights
16.10 GB
KV cache
1.07 GB
Activations
0.81 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 14.6 GBHeadroom: 9.4 GBTTFT: fastollama run qwen3:8b62tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 14.6 GBHeadroom: 9.4 GBTTFT: fast
ollama run qwen3:8b62
tok/s
Estimated
Weights
8.20 GB
KV cache
4.00 GB
Activations
0.42 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 16.0 GBHeadroom: 8.0 GBTTFT: fastollama run gemma4:12b73tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 16.0 GBHeadroom: 8.0 GBTTFT: fast
ollama run gemma4:12b73
tok/s
Estimated
Weights
7.60 GB
KV cache
6.00 GB
Activations
0.39 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~250 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 13.4 GBHeadroom: 10.6 GBTTFT: fastollama run qwen3.5:9b97tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 13.4 GBHeadroom: 10.6 GBTTFT: fast
ollama run qwen3.5:9b97
tok/s
Estimated
Weights
6.60 GB
KV cache
4.50 GB
Activations
0.34 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~188 ms (fast)
Quant: MXFP4Context: 2,048VRAM: 19.3 GBHeadroom: 4.7 GBTTFT: fastollama run gpt-oss:20b25tok/sEstimated
Quant: MXFP4Context: 2,048VRAM: 19.3 GBHeadroom: 4.7 GBTTFT: fast
ollama run gpt-oss:20b25
tok/s
Estimated
Weights
14.00 GB
KV cache
2.61 GB
Activations
0.70 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~436 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 7.1 GBHeadroom: 16.9 GBTTFT: instantollama run llama3.2:3b166tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 7.1 GBHeadroom: 16.9 GBTTFT: instant
ollama run llama3.2:3b166
tok/s
Estimated
Weights
3.40 GB
KV cache
1.50 GB
Activations
0.18 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~63 ms (instant)
Quant: Q4_K_MContext: 8,192VRAM: 3.8 GBHeadroom: 20.2 GBTTFT: instant514tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 3.8 GBHeadroom: 20.2 GBTTFT: instant
514
tok/s
Estimated
Weights
0.90 GB
KV cache
0.85 GB
Activations
0.05 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~35 ms (instant)
Quant: Q4_K_MContext: 8,192VRAM: 17.8 GBHeadroom: 6.2 GBTTFT: fastollama run qwen3:14b62tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 17.8 GBHeadroom: 6.2 GBTTFT: fast
ollama run qwen3:14b62
tok/s
Estimated
Weights
8.40 GB
KV cache
7.00 GB
Activations
0.43 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~292 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 11.0 GBHeadroom: 13.0 GBTTFT: fastollama run qwen2.5:7b71tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 11.0 GBHeadroom: 13.0 GBTTFT: fast
ollama run qwen2.5:7b71
tok/s
Estimated
Weights
8.10 GB
KV cache
0.47 GB
Activations
0.41 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 2.3 GBHeadroom: 21.7 GBTTFT: instant3239tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 2.3 GBHeadroom: 21.7 GBTTFT: instant
3239
tok/s
Estimated
Weights
0.16 GB
KV cache
0.14 GB
Activations
0.02 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~6 ms (instant)
Quant: Q4_K_MContext: 2,048VRAM: 19.7 GBHeadroom: 4.3 GBTTFT: noticeableollama run mistral-small:24b36tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 19.7 GBHeadroom: 4.3 GBTTFT: noticeable
ollama run mistral-small:24b36
tok/s
Estimated
Weights
14.00 GB
KV cache
3.00 GB
Activations
0.70 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~500 ms (noticeable)
Runs with tradeoffs74 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q8_0Context: 8,192VRAM: 50.6 GBHeadroom: 11.8 GBTTFT: noticeable- • Partial CPU offload: ~53% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:30b2tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 50.6 GBHeadroom: 11.8 GBTTFT: noticeable
- • Partial CPU offload: ~53% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:30b2
tok/s
Estimated
Weights
32.00 GB
KV cache
15.00 GB
Activations
1.61 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~625 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 22.5 GBHeadroom: 1.5 GBTTFT: noticeable- • Tight VRAM fit — only 1.5 GB headroom left for context growth
ollama run qwen2.5-coder:32b27tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 22.5 GBHeadroom: 1.5 GBTTFT: noticeable
- • Tight VRAM fit — only 1.5 GB headroom left for context growth
ollama run qwen2.5-coder:32b27
tok/s
Estimated
Weights
19.00 GB
KV cache
0.54 GB
Activations
0.95 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 23.2 GBHeadroom: 0.8 GBTTFT: noticeable- • Tight VRAM fit — only 0.8 GB headroom left for context growth
ollama run qwen3.6:27b32tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 23.2 GBHeadroom: 0.8 GBTTFT: noticeable
- • Tight VRAM fit — only 0.8 GB headroom left for context growth
ollama run qwen3.6:27b32
tok/s
Estimated
Weights
17.00 GB
KV cache
3.38 GB
Activations
0.85 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~563 ms (noticeable)
Quant: Q5_K_MContext: 8,192VRAM: 54.0 GBHeadroom: 8.4 GBTTFT: noticeable- • Partial CPU offload: ~56% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run llama3.3:70b1tok/sEstimated
Quant: Q5_K_MContext: 8,192VRAM: 54.0 GBHeadroom: 8.4 GBTTFT: noticeable
- • Partial CPU offload: ~56% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run llama3.3:70b1
tok/s
Estimated
Weights
47.00 GB
KV cache
2.68 GB
Activations
2.36 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~1459 ms (noticeable)
Quant: Q8_0Context: 8,192VRAM: 53.7 GBHeadroom: 8.7 GBTTFT: noticeable- • Partial CPU offload: ~55% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:32b2tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 53.7 GBHeadroom: 8.7 GBTTFT: noticeable
- • Partial CPU offload: ~55% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:32b2
tok/s
Estimated
Weights
34.00 GB
KV cache
16.00 GB
Activations
1.71 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Quant: Q8_0Context: 8,192VRAM: 52.2 GBHeadroom: 10.2 GBTTFT: noticeable- • Partial CPU offload: ~54% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run gemma4:31b2tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 52.2 GBHeadroom: 10.2 GBTTFT: noticeable
- • Partial CPU offload: ~54% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run gemma4:31b2
tok/s
Estimated
Weights
33.00 GB
KV cache
15.50 GB
Activations
1.66 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~646 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 37.0 GBHeadroom: 25.4 GBTTFT: noticeable- • Partial CPU offload: ~35% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3-coder:30b5tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 37.0 GBHeadroom: 25.4 GBTTFT: noticeable
- • Partial CPU offload: ~35% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3-coder:30b5
tok/s
Estimated
Weights
19.00 GB
KV cache
15.00 GB
Activations
0.96 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~625 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 52.8 GBHeadroom: 9.6 GBTTFT: noticeable- • Partial CPU offload: ~55% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run deepseek-r1:70b1tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 52.8 GBHeadroom: 9.6 GBTTFT: noticeable
- • Partial CPU offload: ~55% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run deepseek-r1:70b1
tok/s
Estimated
Weights
40.00 GB
KV cache
8.75 GB
Activations
2.00 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~1459 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: 80 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 (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 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.