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 / creative

What can AMD Radeon RX 9070 XT run for creative?

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

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

Runs comfortably
137 models

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

#1Hermes 3 Llama 3.2 3B
3B
hermes
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.4 GBHeadroom: 11.6 GB
160
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.00 GB
Model details →
#2Dolphin 3.0 Llama 3.2 3B
3B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.4 GBHeadroom: 11.6 GB
160
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.00 GB
Model details →
#3Gemma 2 2B Instruct
2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.3 GBHeadroom: 12.7 GB
240
tok/s
Estimated
Weights
1.21 GB
KV cache
1.00 GB
Activations
0.07 GB
Runtime
1.00 GB
Model details →
#4Gemma 4 E2B (Effective 2B)
2B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 4.2 GBHeadroom: 11.8 GB
ollama run gemma4:e2b
136
tok/s
Estimated
Weights
2.13 GB
KV cache
1.00 GB
Activations
0.11 GB
Runtime
1.00 GB
Model details →
#5ColPali v1.3
3B
gemma
Commercial OK
Quant: Q4_K_MContext: 0VRAM: 2.9 GBHeadroom: 13.1 GB
160
tok/s
Estimated
Weights
1.81 GB
KV cache
0.00 GB
Activations
0.09 GB
Runtime
1.00 GB
Model details →
#6Qwen 3 1.7B
1.7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.9 GBHeadroom: 13.1 GB
282
tok/s
Estimated
Weights
1.03 GB
KV cache
0.85 GB
Activations
0.06 GB
Runtime
1.00 GB
Model details →
#7mxbai-rerank-large-v2
1.54B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.8 GBHeadroom: 13.2 GB
312
tok/s
Estimated
Weights
0.93 GB
KV cache
0.77 GB
Activations
0.05 GB
Runtime
1.00 GB
Model details →
#8Qwen2-VL 2B Instruct
2B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.3 GBHeadroom: 12.7 GB
240
tok/s
Estimated
Weights
1.21 GB
KV cache
1.00 GB
Activations
0.07 GB
Runtime
1.00 GB
Model details →
#9Qwen 3.5 2B Turkish SFT
2B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.3 GBHeadroom: 12.7 GB
240
tok/s
Estimated
Weights
1.21 GB
KV cache
1.00 GB
Activations
0.07 GB
Runtime
1.00 GB
Model details →
#10Kanarya 2B
2B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.5 GBHeadroom: 13.5 GB
240
tok/s
Estimated
Weights
1.21 GB
KV cache
0.25 GB
Activations
0.06 GB
Runtime
1.00 GB
Model details →
#11SDXL Turbo
2.6B
other
Quant: Q4_K_MContext: 0VRAM: 2.6 GBHeadroom: 13.4 GB
185
tok/s
Estimated
Weights
1.57 GB
KV cache
0.00 GB
Activations
0.08 GB
Runtime
1.00 GB
Model details →
#12Kumru 2B
2.4B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.7 GBHeadroom: 12.3 GB
ollama run alibayram/kumru:latest
200
tok/s
Estimated
Weights
1.45 GB
KV cache
1.20 GB
Activations
0.08 GB
Runtime
1.00 GB
Model details →

Runs with tradeoffs
65 models

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

Hermes 3 Llama 3.1 8B
8B
hermes
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 13.9 GBHeadroom: 2.1 GB
  • • Tight VRAM fit — only 2.1 GB headroom left for context growth
ollama run hermes3:8b
34
tok/s
Estimated
Weights
8.50 GB
KV cache
4.00 GB
Activations
0.43 GB
Runtime
1.00 GB
Model details →
Gemma 2 9B Instruct
9B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 15.5 GBHeadroom: 0.5 GB
  • • Tight VRAM fit — only 0.5 GB headroom left for context growth
ollama run gemma2:9b
30
tok/s
Estimated
Weights
9.56 GB
KV cache
4.50 GB
Activations
0.49 GB
Runtime
1.00 GB
Model details →
DeepSeek V2 Lite Chat
15.7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 12.9 GBHeadroom: 3.1 GB
  • • Tight VRAM fit — only 3.1 GB headroom left for context growth
200
tok/s
Estimated
Weights
9.48 GB
KV cache
1.96 GB
Activations
0.48 GB
Runtime
1.00 GB
Model details →
DeepSeek V3 Lite (16B MoE)
16B
deepseek
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
200
tok/s
Estimated
Weights
9.66 GB
KV cache
2.00 GB
Activations
0.49 GB
Runtime
1.00 GB
Model details →
Granite 3 MoE (3B active)
16B
granite
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
160
tok/s
Estimated
Weights
9.66 GB
KV cache
2.00 GB
Activations
0.49 GB
Runtime
1.00 GB
Model details →
DeepSeek MoE 16B Base
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 15.1 GBHeadroom: 0.9 GB
  • • Tight VRAM fit — only 0.9 GB headroom left for context growth
200
tok/s
Estimated
Weights
9.66 GB
KV cache
4.00 GB
Activations
0.49 GB
Runtime
1.00 GB
Model details →
Dolphin 3.0 Mistral 24B
24B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 28.2 GBHeadroom: 7.0 GB
  • • Partial CPU offload: ~43% of layers run on CPU
ollama run dolphin-mistral:24b
20
tok/s
Estimated
Weights
14.49 GB
KV cache
12.00 GB
Activations
0.73 GB
Runtime
1.00 GB
Model details →
Gemma 3 12B
12B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 14.6 GBHeadroom: 1.4 GB
  • • Tight VRAM fit — only 1.4 GB headroom left for context growth
ollama run gemma3:12b
40
tok/s
Estimated
Weights
7.25 GB
KV cache
6.00 GB
Activations
0.37 GB
Runtime
1.00 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: 49 new comfortable, 82 new tradeoff

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
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: 64 new comfortable

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
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: 99 new comfortable

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
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.