What can AMD Radeon RX 9070 XT run for chat?

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
129 models

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

#1Qwen 3 0.6B
0.6B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.6 GBHeadroom: 13.4 GB
978
tok/s
Estimated
Weights
0.30 GB
KV cache
0.30 GB
Activations
0.02 GB
Runtime
2.00 GB
#2Qwen 3 1.7B
1.7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.8 GBHeadroom: 12.2 GB
345
tok/s
Estimated
Weights
0.90 GB
KV cache
0.85 GB
Activations
0.05 GB
Runtime
2.00 GB
#3TinyLlama 1.1B Chat v1.0
1.1B
llama
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.8 GBHeadroom: 13.2 GB
533
tok/s
Estimated
Weights
0.60 GB
KV cache
0.14 GB
Activations
0.03 GB
Runtime
2.00 GB
#4Gemma 2 2B Instruct
2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.2 GBHeadroom: 11.8 GB
293
tok/s
Estimated
Weights
1.10 GB
KV cache
1.00 GB
Activations
0.06 GB
Runtime
2.00 GB
#5Kumru 2B
2.4B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.8 GBHeadroom: 11.2 GB
ollama run alibayram/kumru:latest
244
tok/s
Estimated
Weights
1.50 GB
KV cache
1.20 GB
Activations
0.08 GB
Runtime
2.00 GB
#6TinyLlama 1.1B Chat v0.3 AWQ
1.1B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.8 GBHeadroom: 13.2 GB
533
tok/s
Estimated
Weights
0.60 GB
KV cache
0.14 GB
Activations
0.03 GB
Runtime
2.00 GB
#7TinyLlama 1.1B Chat v0.3 GPTQ
1.1B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.8 GBHeadroom: 13.2 GB
533
tok/s
Estimated
Weights
0.60 GB
KV cache
0.14 GB
Activations
0.03 GB
Runtime
2.00 GB
Quant: Q4_K_MContext: 8,192VRAM: 4.6 GBHeadroom: 11.4 GB
244
tok/s
Estimated
Weights
1.30 GB
KV cache
1.20 GB
Activations
0.07 GB
Runtime
2.00 GB
#9Falcon 3 3B Instruct
3B
falcon
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.3 GBHeadroom: 10.7 GB
196
tok/s
Estimated
Weights
1.70 GB
KV cache
1.50 GB
Activations
0.09 GB
Runtime
2.00 GB
#10PhoGPT 4B Chat
3.7B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 6.0 GBHeadroom: 10.0 GB
159
tok/s
Estimated
Weights
2.00 GB
KV cache
1.85 GB
Activations
0.11 GB
Runtime
2.00 GB
#11Salamandra 2B Instruct
2B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.2 GBHeadroom: 11.8 GB
293
tok/s
Estimated
Weights
1.10 GB
KV cache
1.00 GB
Activations
0.06 GB
Runtime
2.00 GB
#12PhoGPT 4B
3.7B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 6.0 GBHeadroom: 10.0 GB
159
tok/s
Estimated
Weights
2.00 GB
KV cache
1.85 GB
Activations
0.11 GB
Runtime
2.00 GB

Runs with tradeoffs
98 models

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

DeepSeek V2 Lite Chat
15.7B
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
244
tok/s
Estimated
Weights
8.60 GB
KV cache
1.96 GB
Activations
0.43 GB
Runtime
2.00 GB
Gemma 2 9B Instruct
9B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 12.6 GBHeadroom: 3.4 GB
  • Tight VRAM fit — only 3.4 GB headroom left for context growth
ollama run gemma2:9b
65
tok/s
Estimated
Weights
5.80 GB
KV cache
4.50 GB
Activations
0.30 GB
Runtime
2.00 GB
Bielik 11B v3.0 Instruct GGUF
11B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 13.9 GBHeadroom: 2.1 GB
  • Tight VRAM fit — only 2.1 GB headroom left for context growth
53
tok/s
Estimated
Weights
6.10 GB
KV cache
5.50 GB
Activations
0.31 GB
Runtime
2.00 GB
Mistral Nemo 12B Instruct
12B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 15.9 GBHeadroom: 0.1 GB
  • Tight VRAM fit — only 0.1 GB headroom left for context growth
ollama run mistral-nemo:12b
49
tok/s
Estimated
Weights
7.50 GB
KV cache
6.00 GB
Activations
0.38 GB
Runtime
2.00 GB
Gemma 3 12B
12B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 15.7 GBHeadroom: 0.3 GB
  • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run gemma3:12b
49
tok/s
Estimated
Weights
7.30 GB
KV cache
6.00 GB
Activations
0.37 GB
Runtime
2.00 GB
Quant: Q4_K_MContext: 4,096VRAM: 12.6 GBHeadroom: 3.4 GB
  • Tight VRAM fit — only 3.4 GB headroom left for context growth
49
tok/s
Estimated
Weights
7.20 GB
KV cache
3.00 GB
Activations
0.36 GB
Runtime
2.00 GB
OpenThaiGPT 1.0.0 Beta 13B Chat
13B
llama
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 12.8 GBHeadroom: 3.2 GB
  • Tight VRAM fit — only 3.2 GB headroom left for context growth
45
tok/s
Estimated
Weights
7.20 GB
KV cache
3.25 GB
Activations
0.36 GB
Runtime
2.00 GB
Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 12.6 GBHeadroom: 3.4 GB
  • Tight VRAM fit — only 3.4 GB headroom left for context growth
ollama run qwen3:14b
42
tok/s
Estimated
Weights
8.40 GB
KV cache
1.75 GB
Activations
0.42 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: 9 new comfortable, 116 new tradeoff

  • Gemma 3 270M
  • SmolLM2 135M Instruct
  • SmolLM2 360M Instruct
  • VBART Large (Turkish Summarization)

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: 31 new comfortable

  • Llama 3.1 8B Instruct
  • Gemma 4 12B
  • Qwen3.5 9B
  • Gemma 3 270M

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: 86 new comfortable

  • Llama 3.1 8B Instruct
  • 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.