What can AMD Radeon RX 7900 XTX run for agents?
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 agents use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q8_0Context: 8,192VRAM: 14.9 GBHeadroom: 9.1 GBTTFT: fastollama run hermes3:8b62tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 14.9 GBHeadroom: 9.1 GBTTFT: fast
ollama run hermes3:8b62
tok/s
Estimated
Weights
8.50 GB
KV cache
4.00 GB
Activations
0.43 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Quant: Q4_K_MContext: 2,048VRAM: 19.7 GBHeadroom: 4.3 GBTTFT: noticeableollama run dolphin-mistral:24b36tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 19.7 GBHeadroom: 4.3 GBTTFT: noticeable
ollama run dolphin-mistral: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)
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: Q5_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 13.1 GBTTFT: fastollama run mistral:7b110tok/sEstimated
Quant: Q5_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 13.1 GBTTFT: fast
ollama run mistral:7b110
tok/s
Estimated
Weights
5.10 GB
KV cache
3.50 GB
Activations
0.26 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
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: 12.4 GBHeadroom: 11.6 GBTTFT: fastollama run ornith:9b97tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 12.4 GBHeadroom: 11.6 GBTTFT: fast
ollama run ornith:9b97
tok/s
Estimated
Weights
5.60 GB
KV cache
4.50 GB
Activations
0.29 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~188 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 16.5 GBHeadroom: 7.5 GBTTFT: fastollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M72tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 16.5 GBHeadroom: 7.5 GBTTFT: fast
ollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M72
tok/s
Estimated
Weights
8.00 GB
KV cache
6.08 GB
Activations
0.41 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~253 ms (fast)
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)
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: Q4_K_MContext: 8,192VRAM: 11.3 GBHeadroom: 12.7 GBTTFT: fastollama run dolphin3:8b109tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.3 GBHeadroom: 12.7 GBTTFT: fast
ollama run dolphin3:8b109
tok/s
Estimated
Weights
5.00 GB
KV cache
4.00 GB
Activations
0.26 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~167 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: Q5_K_MContext: 8,192VRAM: 20.0 GBHeadroom: 4.0 GBTTFT: fast- • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run qwen2.5:14b55tok/sEstimated
Quant: Q5_K_MContext: 8,192VRAM: 20.0 GBHeadroom: 4.0 GBTTFT: fast
- • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run qwen2.5:14b55
tok/s
Estimated
Weights
10.50 GB
KV cache
7.00 GB
Activations
0.53 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~292 ms (fast)
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: 22.1 GBHeadroom: 1.9 GBTTFT: noticeable- • Tight VRAM fit — only 1.9 GB headroom left for context growth
ollama run gemma4:26b-moe34tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 22.1 GBHeadroom: 1.9 GBTTFT: noticeable
- • Tight VRAM fit — only 1.9 GB headroom left for context growth
ollama run gemma4:26b-moe34
tok/s
Estimated
Weights
16.00 GB
KV cache
3.25 GB
Activations
0.80 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~542 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: 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 north-mini-code-1.05tok/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 north-mini-code-1.05
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: 8,192VRAM: 37.5 GBHeadroom: 24.9 GBTTFT: noticeable- • Partial CPU offload: ~36% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run glm-4.7-flash5tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 37.5 GBHeadroom: 24.9 GBTTFT: noticeable
- • Partial CPU offload: ~36% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run glm-4.7-flash5
tok/s
Estimated
Weights
19.00 GB
KV cache
15.50 GB
Activations
0.96 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~646 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 39.5 GBHeadroom: 22.9 GBTTFT: noticeable- • Partial CPU offload: ~39% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run laguna-xs-2.14tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 39.5 GBHeadroom: 22.9 GBTTFT: noticeable
- • Partial CPU offload: ~39% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run laguna-xs-2.14
tok/s
Estimated
Weights
20.00 GB
KV cache
16.50 GB
Activations
1.01 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~688 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 41.6 GBHeadroom: 20.8 GBTTFT: noticeable- • Partial CPU offload: ~42% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run ornith:35b4tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 41.6 GBHeadroom: 20.8 GBTTFT: noticeable
- • Partial CPU offload: ~42% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run ornith:35b4
tok/s
Estimated
Weights
21.00 GB
KV cache
17.50 GB
Activations
1.06 GB
Runtime
2.00 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: 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.