RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
Will it run? / AMD Radeon RX 9070 XT

What can AMD Radeon RX 9070 XT run?

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

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

Runs comfortably
171 models

Full-VRAM resident, with room for context. No compromises.

#1all-MiniLM-L6-v2
0.022B
other
Commercial OK
Quant: Q4_K_MContext: 256VRAM: 2.0 GBHeadroom: 14.0 GB
26667
tok/s
Estimated
Weights
0.01 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
2.00 GB
Model details →
#2Piper
0.025B
other
Commercial OK
Quant: Q4_K_MContext: 0VRAM: 2.0 GBHeadroom: 14.0 GB
23467
tok/s
Estimated
Weights
0.02 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
2.00 GB
Model details →
#3Whisper Tiny
0.039B
other
Commercial OK
Quant: Q4_K_MContext: 30VRAM: 2.0 GBHeadroom: 14.0 GB
15043
tok/s
Estimated
Weights
0.02 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
2.00 GB
Model details →
#4Whisper Base
0.074B
other
Commercial OK
Quant: Q4_K_MContext: 30VRAM: 2.0 GBHeadroom: 14.0 GB
7928
tok/s
Estimated
Weights
0.04 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
2.00 GB
Model details →
#5Kokoro 82M
0.082B
other
Commercial OK
Quant: Q4_K_MContext: 0VRAM: 2.1 GBHeadroom: 13.9 GB
7154
tok/s
Estimated
Weights
0.05 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
2.00 GB
Model details →
#6all-mpnet-base-v2
0.109B
other
Commercial OK
Quant: Q4_K_MContext: 384VRAM: 2.1 GBHeadroom: 13.9 GB
5382
tok/s
Estimated
Weights
0.07 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
2.00 GB
Model details →
#7paraphrase-multilingual-MiniLM-L12-v2
0.118B
other
Commercial OK
Quant: Q4_K_MContext: 128VRAM: 2.1 GBHeadroom: 13.9 GB
4972
tok/s
Estimated
Weights
0.07 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
2.00 GB
Model details →
#8Nomic Embed Text v1.5
0.137B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.2 GBHeadroom: 13.8 GB
4282
tok/s
Estimated
Weights
0.08 GB
KV cache
0.07 GB
Activations
0.01 GB
Runtime
2.00 GB
Model details →
#9SmolLM2 135M Instruct
0.135B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.2 GBHeadroom: 13.8 GB
4346
tok/s
Estimated
Weights
0.08 GB
KV cache
0.07 GB
Activations
0.01 GB
Runtime
2.00 GB
Model details →
#10GTE ModernBERT Base
0.149B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.2 GBHeadroom: 13.8 GB
3937
tok/s
Estimated
Weights
0.09 GB
KV cache
0.07 GB
Activations
0.01 GB
Runtime
2.00 GB
Model details →
#11Whisper Small
0.244B
other
Commercial OK
Quant: Q4_K_MContext: 30VRAM: 2.2 GBHeadroom: 13.8 GB
2404
tok/s
Estimated
Weights
0.15 GB
KV cache
0.00 GB
Activations
0.01 GB
Runtime
2.00 GB
Model details →
#12Gemma 3 270M
0.27B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.3 GBHeadroom: 13.7 GB
2173
tok/s
Estimated
Weights
0.16 GB
KV cache
0.14 GB
Activations
0.02 GB
Runtime
2.00 GB
Model details →

Runs with tradeoffs
80 models

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

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
Model details →
Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 24.8 GBHeadroom: 10.4 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
18.11 GB
KV cache
3.75 GB
Activations
0.91 GB
Runtime
2.00 GB
Model details →
Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 24.4 GBHeadroom: 10.8 GB
  • • Partial CPU offload: ~35% 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
19.32 GB
KV cache
2.15 GB
Activations
0.97 GB
Runtime
2.00 GB
Model details →
Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 26.3 GBHeadroom: 8.9 GB
  • • Partial CPU offload: ~39% 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
19.32 GB
KV cache
4.00 GB
Activations
0.97 GB
Runtime
2.00 GB
Model details →
Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 25.5 GBHeadroom: 9.7 GB
  • • Partial CPU offload: ~37% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run gemma4:31b
3
tok/s
Estimated
Weights
18.72 GB
KV cache
3.88 GB
Activations
0.94 GB
Runtime
2.00 GB
Model details →
Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.9 GBHeadroom: 1.1 GB
  • • Tight VRAM fit — only 1.1 GB headroom left for context growth
ollama run qwen3:8b
42
tok/s
Estimated
Weights
8.50 GB
KV cache
4.00 GB
Activations
0.43 GB
Runtime
2.00 GB
Model details →
DeepSeek R1 Distill Qwen 32B
32B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 26.3 GBHeadroom: 8.9 GB
  • • Partial CPU offload: ~39% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run deepseek-r1:32b
3
tok/s
Estimated
Weights
19.32 GB
KV cache
4.00 GB
Activations
0.97 GB
Runtime
2.00 GB
Model details →
Gemma 4 26B MoE
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 31.5 GBHeadroom: 3.7 GB
  • • Partial CPU offload: ~49% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run gemma4:26b-moe
3
tok/s
Estimated
Weights
15.70 GB
KV cache
13.00 GB
Activations
0.79 GB
Runtime
2.00 GB
Model details →

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: 90 new tradeoff

  • • Llama 3.1 8B Instruct
  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Llama 3.3 70B Instruct
Shop this upgrade↗

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: 21 new comfortable

  • • Turkish Gemma 9B T1
  • • NVIDIA Nemotron Nano 9B v2 Japanese
  • • YTU Turkish Gemma 9B v0.1
  • • DeepSeek R1 Distill Qwen 7B
Shop this upgrade↗

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: 62 new comfortable

  • • DeepSeek V2 Lite Chat
  • • Turkish Gemma 9B T1
  • • NVIDIA Nemotron Nano 9B v2 Japanese
  • • YTU Turkish Gemma 9B v0.1
Shop this upgrade↗

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.

—
DeepSeek V4 Flash (284B MoE)
284B
deepseek
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.