What can AMD Radeon RX 9070 XT run for coding?

Build: AMD Radeon RX 9070 XT + — + 32 GB RAM (windows)

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

Runs comfortably
113 models

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

#1CodeGemma 7B
7B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 8.9 GBHeadroom: 7.1 GB
ollama run codegemma:7b
69
tok/s
Estimated
Weights
4.20 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.00 GB
#2Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.0 GBHeadroom: 6.0 GB
ollama run qwen3:8b
60
tok/s
Estimated
Weights
4.80 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.00 GB
#3Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 11.6 GBHeadroom: 4.4 GB
ollama run qwen3:14b
34
tok/s
Estimated
Weights
8.40 GB
KV cache
1.75 GB
Activations
0.42 GB
Runtime
1.00 GB
#4Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.0 GBHeadroom: 6.0 GB
ollama run qwen2.5:7b
39
tok/s
Estimated
Weights
8.10 GB
KV cache
0.47 GB
Activations
0.41 GB
Runtime
1.00 GB
#5Llama 3.1 8B Instruct
8B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 11.0 GBHeadroom: 5.0 GB
ollama run llama3.1:8b
34
tok/s
Estimated
Weights
8.50 GB
KV cache
1.07 GB
Activations
0.43 GB
Runtime
1.00 GB
#6StarCoder 2 3B
3B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.6 GBHeadroom: 11.4 GB
160
tok/s
Estimated
Weights
2.00 GB
KV cache
1.50 GB
Activations
0.11 GB
Runtime
1.00 GB
#7Qwen 2.5 Coder 3B
3B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.5 GBHeadroom: 11.5 GB
160
tok/s
Estimated
Weights
1.90 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.00 GB
#8StarCoder 2 7B
7B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.1 GBHeadroom: 6.9 GB
69
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
1.00 GB
#9Codestral Mamba 7B
7B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 8.9 GBHeadroom: 7.1 GB
69
tok/s
Estimated
Weights
4.20 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.00 GB
#10Gervásio 8B PTPT
8B
llama
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 7.6 GBHeadroom: 8.4 GB
60
tok/s
Estimated
Weights
4.40 GB
KV cache
2.00 GB
Activations
0.22 GB
Runtime
1.00 GB
#11OpenCoder 8B
8B
opencoder
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GB
60
tok/s
Estimated
Weights
4.70 GB
KV cache
4.00 GB
Activations
0.24 GB
Runtime
1.00 GB
#12Yi Coder 9B
9B
yi
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.2 GBHeadroom: 4.8 GB
53
tok/s
Estimated
Weights
5.40 GB
KV cache
4.50 GB
Activations
0.28 GB
Runtime
1.00 GB

Runs with tradeoffs
83 models

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

DeepSeek Coder V2 Lite (16B)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 13.0 GBHeadroom: 3.0 GB
  • Tight VRAM fit — only 3.0 GB headroom left for context growth
ollama run deepseek-coder-v2:16b
30
tok/s
Estimated
Weights
9.50 GB
KV cache
2.00 GB
Activations
0.48 GB
Runtime
1.00 GB
Codestral 22B
22B
mistral
Quant: Q4_K_MContext: 8,192VRAM: 25.7 GBHeadroom: 9.5 GB
  • Partial CPU offload: ~38% of layers run on CPU
ollama run codestral:22b
22
tok/s
Estimated
Weights
13.00 GB
KV cache
11.00 GB
Activations
0.66 GB
Runtime
1.00 GB
Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 12.1 GBHeadroom: 3.9 GB
  • Tight VRAM fit — only 3.9 GB headroom left for context growth
ollama run qwen2.5:14b
34
tok/s
Estimated
Weights
8.90 GB
KV cache
1.75 GB
Activations
0.45 GB
Runtime
1.00 GB
Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 23.1 GBHeadroom: 12.1 GB
  • Partial CPU offload: ~31% of layers run on CPU
ollama run qwen2.5-coder:32b
15
tok/s
Estimated
Weights
19.00 GB
KV cache
2.15 GB
Activations
0.96 GB
Runtime
1.00 GB
Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 34.9 GBHeadroom: 0.3 GB
  • Partial CPU offload: ~54% of layers run on CPU
ollama run qwen3:30b
16
tok/s
Estimated
Weights
18.00 GB
KV cache
15.00 GB
Activations
0.91 GB
Runtime
1.00 GB
Muse Glimmer 30B
30B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 19.6 GBHeadroom: 15.6 GB
  • Partial CPU offload: ~18% of layers run on CPU
ollama run muse-glimmer
16
tok/s
Estimated
Weights
17.00 GB
KV cache
0.71 GB
Activations
0.86 GB
Runtime
1.00 GB
Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 23.8 GBHeadroom: 11.4 GB
  • Partial CPU offload: ~33% of layers run on CPU
ollama run gemma4:31b
15
tok/s
Estimated
Weights
18.00 GB
KV cache
3.88 GB
Activations
0.90 GB
Runtime
1.00 GB
Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 25.0 GBHeadroom: 10.2 GB
  • Partial CPU offload: ~36% of layers run on CPU
ollama run qwen3:32b
15
tok/s
Estimated
Weights
19.00 GB
KV cache
4.00 GB
Activations
0.95 GB
Runtime
1.00 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: 41 new comfortable, 102 new tradeoff

  • Qwen 3 0.6B
  • Qwen 3 1.7B
  • Gemma 3 270M
  • SmolLM2 135M Instruct

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: 56 new comfortable

  • Qwen 3 0.6B
  • Gemma 4 12B
  • Qwen3.5 9B
  • Qwen 3 1.7B

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: 112 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 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.