What can AMD Radeon RX 9070 XT run for agents?

Build: RX 9070 XT + Ryzen 7 9700X + 32GB DDR5 (Linux/ROCm)

Memory: 16 GB VRAM + 32 GB system RAM
Runner: llama.cpp (ROCm)

Runs comfortably
74 models

Ranked by fit for agents use case + predicted speed. Click a row for VRAM breakdown.

#1Hermes 3 Llama 3.1 8B
8B
hermes
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.2 GBHeadroom: 4.8 GB
ollama run hermes3:8b
73
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
2.00 GB
#2Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 11.0 GBHeadroom: 5.0 GB
ollama run qwen2.5:7b
48
tok/s
Estimated
Weights
8.10 GB
KV cache
0.47 GB
Activations
0.41 GB
Runtime
2.00 GB
#3Mistral 7B Instruct v0.3
7B
mistral
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 5.1 GB
ollama run mistral:7b
74
tok/s
Estimated
Weights
5.10 GB
KV cache
3.50 GB
Activations
0.26 GB
Runtime
2.00 GB
#4Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.2 GBHeadroom: 4.8 GB
73
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
2.00 GB
#5Mellum2 12B-A2.5B
12.15B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 11.9 GBHeadroom: 4.1 GB
ollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M
48
tok/s
Estimated
Weights
8.00 GB
KV cache
1.52 GB
Activations
0.40 GB
Runtime
2.00 GB
#6Dolphin 3.0 8B
8B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.3 GBHeadroom: 4.7 GB
ollama run dolphin3:8b
73
tok/s
Estimated
Weights
5.00 GB
KV cache
4.00 GB
Activations
0.26 GB
Runtime
2.00 GB
#7Qwen 2.5 Math 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 8.4 GBHeadroom: 7.6 GB
84
tok/s
Estimated
Weights
4.40 GB
KV cache
1.75 GB
Activations
0.22 GB
Runtime
2.00 GB
#8Qwen 3 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 5.9 GB
84
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
2.00 GB
#9CodeQwen 1.5 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 5.9 GB
84
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
2.00 GB
#10Qwen 2-VL 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.3 GBHeadroom: 5.7 GB
84
tok/s
Estimated
Weights
4.60 GB
KV cache
3.50 GB
Activations
0.24 GB
Runtime
2.00 GB
#11Qwen 2.5-VL 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 5.9 GB
84
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
2.00 GB
#12Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GB
ollama run qwen3:8b
73
tok/s
Estimated
Weights
4.80 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
2.00 GB

Runs with tradeoffs
98 models

Tight VRAM, partial CPU offload, or context-limited.

Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 13.1 GBHeadroom: 2.9 GB
  • Tight VRAM fit — only 2.9 GB headroom left for context growth
ollama run qwen2.5:14b
42
tok/s
Estimated
Weights
8.90 GB
KV cache
1.75 GB
Activations
0.45 GB
Runtime
2.00 GB
Ornith 1.0 9B
9B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 12.4 GBHeadroom: 3.6 GB
  • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run ornith:9b
65
tok/s
Estimated
Weights
5.60 GB
KV cache
4.50 GB
Activations
0.29 GB
Runtime
2.00 GB
Llama 3.1 8B Instruct
8B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 12.0 GBHeadroom: 4.0 GB
  • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run llama3.1:8b
42
tok/s
Estimated
Weights
8.50 GB
KV cache
1.07 GB
Activations
0.43 GB
Runtime
2.00 GB
Dolphin 3.0 Mistral 24B
24B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 28.7 GBHeadroom: 6.5 GB
  • Partial CPU offload: ~44% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run dolphin-mistral:24b
4
tok/s
Estimated
Weights
14.00 GB
KV cache
12.00 GB
Activations
0.71 GB
Runtime
2.00 GB
Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 24.7 GBHeadroom: 10.5 GB
  • Partial CPU offload: ~35% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:30b
4
tok/s
Estimated
Weights
18.00 GB
KV cache
3.75 GB
Activations
0.90 GB
Runtime
2.00 GB
Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 24.1 GBHeadroom: 11.1 GB
  • Partial CPU offload: ~34% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen2.5-coder:32b
4
tok/s
Estimated
Weights
19.00 GB
KV cache
2.15 GB
Activations
0.96 GB
Runtime
2.00 GB
Qwen3 Coder 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 25.7 GBHeadroom: 9.5 GB
  • Partial CPU offload: ~38% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3-coder:30b
4
tok/s
Estimated
Weights
19.00 GB
KV cache
3.75 GB
Activations
0.95 GB
Runtime
2.00 GB
Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 26.0 GBHeadroom: 9.2 GB
  • Partial CPU offload: ~38% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:32b
3
tok/s
Estimated
Weights
19.00 GB
KV cache
4.00 GB
Activations
0.95 GB
Runtime
2.00 GB

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, 116 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: 86 new comfortable

  • Qwen 3 0.6B
  • Llama 3.1 8B Instruct
  • Gemma 4 12B
  • Qwen3.5 9B

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: 141 new comfortable

  • Qwen 3 0.6B
  • Llama 3.1 8B Instruct
  • Qwen 3 30B-A3B
  • Qwen 2.5 Coder 32B Instruct

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)
1600B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

Llama 4 Scout
109B
llama
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 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.

RunLocalAI Will-It-Run Framework →

Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.