What can AMD Radeon RX 7900 XTX run for reasoning?
Build: RX 7900 XTX + Ryzen 9 7950X + 64GB DDR5 (Linux/ROCm)
Memory: 24 GB VRAM + 64 GB system RAM
Runner: llama.cpp (ROCm)
Runs comfortably119 models
Ranked by fit for reasoning use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q4_K_MContext: 8,192VRAM: 11.2 GBHeadroom: 12.8 GBTTFT: fast109tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.2 GBHeadroom: 12.8 GBTTFT: fast
109
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 11.2 GBHeadroom: 12.8 GBTTFT: fastollama run RefinedNeuro/RN_TR_R1:latest109tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.2 GBHeadroom: 12.8 GBTTFT: fast
ollama run RefinedNeuro/RN_TR_R1:latest109
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 13.1 GBTTFT: fast109tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 13.1 GBTTFT: fast
109
tok/s
Estimated
Weights
4.70 GB
KV cache
4.00 GB
Activations
0.24 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 11.8 GBHeadroom: 12.2 GBTTFT: fast97tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.8 GBHeadroom: 12.2 GBTTFT: fast
97
tok/s
Estimated
Weights
5.00 GB
KV cache
4.50 GB
Activations
0.26 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~188 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 14.0 GBHeadroom: 10.0 GBTTFT: fastollama run deepseek-r1:7b71tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 14.0 GBHeadroom: 10.0 GBTTFT: fast
ollama run deepseek-r1:7b71
tok/s
Estimated
Weights
8.10 GB
KV cache
3.50 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: 17.8 GBHeadroom: 6.2 GBTTFT: fastollama run phi4-reasoning:14b62tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 17.8 GBHeadroom: 6.2 GBTTFT: fast
ollama run phi4-reasoning: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: Q4_K_MContext: 8,192VRAM: 17.8 GBHeadroom: 6.2 GBTTFT: fastollama run deepseek-r1:14b62tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 17.8 GBHeadroom: 6.2 GBTTFT: fast
ollama run deepseek-r1:14b62
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: Q4_K_MContext: 8,192VRAM: 20.0 GBHeadroom: 4.0 GBTTFT: instant364tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 20.0 GBHeadroom: 4.0 GBTTFT: instant
364
tok/s
Estimated
Weights
9.50 GB
KV cache
8.00 GB
Activations
0.48 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~50 ms (instant)
Quant: Q4_K_MContext: 2,048VRAM: 19.7 GBHeadroom: 4.3 GBTTFT: noticeable36tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 19.7 GBHeadroom: 4.3 GBTTFT: noticeable
36
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)
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 13.9 GBTTFT: fast125tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 13.9 GBTTFT: fast
125
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Quant: Q4_K_MContext: 4,096VRAM: 8.4 GBHeadroom: 15.6 GBTTFT: fast125tok/sEstimated
Quant: Q4_K_MContext: 4,096VRAM: 8.4 GBHeadroom: 15.6 GBTTFT: fast
125
tok/s
Estimated
Weights
4.40 GB
KV cache
1.75 GB
Activations
0.22 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 13.9 GBTTFT: fast125tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 13.9 GBTTFT: fast
125
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Runs with tradeoffs74 models
Tight VRAM, partial CPU offload, or context-limited.
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
28tok/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
28
tok/s
Estimated
Weights
17.10 GB
KV cache
3.88 GB
Activations
0.86 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~646 ms (noticeable)
Quant: Q4_K_MContext: 4,096VRAM: 21.9 GBHeadroom: 2.1 GBTTFT: noticeable- • Tight VRAM fit — only 2.1 GB headroom left for context growth
36tok/sEstimated
Quant: Q4_K_MContext: 4,096VRAM: 21.9 GBHeadroom: 2.1 GBTTFT: noticeable
- • Tight VRAM fit — only 2.1 GB headroom left for context growth
36
tok/s
Estimated
Weights
13.20 GB
KV cache
6.00 GB
Activations
0.66 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~500 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 38.0 GBHeadroom: 24.4 GBTTFT: noticeable- • Partial CPU offload: ~37% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwq:32b5tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 38.0 GBHeadroom: 24.4 GBTTFT: noticeable
- • Partial CPU offload: ~37% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwq:32b5
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 36.5 GBHeadroom: 25.9 GBTTFT: noticeable- • Partial CPU offload: ~34% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
5tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 36.5 GBHeadroom: 25.9 GBTTFT: noticeable
- • Partial CPU offload: ~34% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
5
tok/s
Estimated
Weights
17.60 GB
KV cache
16.00 GB
Activations
0.89 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 36.5 GBHeadroom: 25.9 GBTTFT: noticeable- • Partial CPU offload: ~34% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
5tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 36.5 GBHeadroom: 25.9 GBTTFT: noticeable
- • Partial CPU offload: ~34% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
5
tok/s
Estimated
Weights
17.60 GB
KV cache
16.00 GB
Activations
0.89 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Quant: AWQ-INT4Context: 8,192VRAM: 38.0 GBHeadroom: 24.4 GBTTFT: noticeable- • Partial CPU offload: ~37% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3tok/sEstimated
Quant: AWQ-INT4Context: 8,192VRAM: 38.0 GBHeadroom: 24.4 GBTTFT: noticeable
- • Partial CPU offload: ~37% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Quant: AWQ-INT4Context: 8,192VRAM: 38.0 GBHeadroom: 24.4 GBTTFT: noticeable- • Partial CPU offload: ~37% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3tok/sEstimated
Quant: AWQ-INT4Context: 8,192VRAM: 38.0 GBHeadroom: 24.4 GBTTFT: noticeable
- • Partial CPU offload: ~37% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Quant: AWQ-INT4Context: 8,192VRAM: 38.0 GBHeadroom: 24.4 GBTTFT: noticeable- • Partial CPU offload: ~37% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3tok/sEstimated
Quant: AWQ-INT4Context: 8,192VRAM: 38.0 GBHeadroom: 24.4 GBTTFT: noticeable
- • Partial CPU offload: ~37% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~667 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: 64 new comfortable, 80 new tradeoff
- • Qwen 3 0.6B
- • Llama 3.2 3B Instruct
- • Qwen 3 1.7B
- • Gemma 3 270M
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: 135 new comfortable
- • Qwen 3 0.6B
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen3.6 27B
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: 117 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 (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.