What can AMD Radeon RX 7900 XTX run for creative?

Build: RX 7900 XTX + Ryzen 9 7950X + 64GB DDR5 (Linux/ROCm)

Memory: 24 GB VRAM + 64 GB system RAM
Runner: llama.cpp (ROCm)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
160 models

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

#1Hermes 3 Llama 3.1 8B
8B
hermes
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.9 GBHeadroom: 9.1 GBTTFT: fast
ollama run hermes3:8b
62
tok/s
Estimated
Weights
8.50 GB
KV cache
4.00 GB
Activations
0.43 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Model details →
#2Gemma 2 9B Instruct
9B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 16.8 GBHeadroom: 7.2 GBTTFT: fast
ollama run gemma2:9b
55
tok/s
Estimated
Weights
9.80 GB
KV cache
4.50 GB
Activations
0.50 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~188 ms (fast)
Model details →
#3Hermes 3 Llama 3.2 3B
3B
hermes
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.4 GBHeadroom: 18.6 GBTTFT: instant
292
tok/s
Estimated
Weights
1.80 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~63 ms (instant)
Model details →
#4Dolphin 3.0 Llama 3.2 3B
3B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.4 GBHeadroom: 18.6 GBTTFT: instant
292
tok/s
Estimated
Weights
1.80 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~63 ms (instant)
Model details →
#5Dolphin 3.0 8B
8B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.3 GBHeadroom: 12.7 GBTTFT: fast
ollama run dolphin3:8b
109
tok/s
Estimated
Weights
5.00 GB
KV cache
4.00 GB
Activations
0.26 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Model details →
#6Gemma 4 E4B (Effective 4B)
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 8.6 GBHeadroom: 15.4 GBTTFT: instant
ollama run gemma4:e4b
124
tok/s
Estimated
Weights
4.40 GB
KV cache
2.00 GB
Activations
0.23 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~83 ms (instant)
Model details →
#7Gemma 2 2B Instruct
2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.2 GBHeadroom: 19.8 GBTTFT: instant
437
tok/s
Estimated
Weights
1.10 GB
KV cache
1.00 GB
Activations
0.06 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~42 ms (instant)
Model details →
#8Gemma 3 4B
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 8.6 GBHeadroom: 15.4 GBTTFT: instant
ollama run gemma3:4b
124
tok/s
Estimated
Weights
4.40 GB
KV cache
2.00 GB
Activations
0.23 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~83 ms (instant)
Model details →
#9Gemma 4 E2B (Effective 2B)
2B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 5.3 GBHeadroom: 18.7 GBTTFT: instant
ollama run gemma4:e2b
248
tok/s
Estimated
Weights
2.20 GB
KV cache
1.00 GB
Activations
0.12 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~42 ms (instant)
Model details →
#10CodeGemma 7B
7B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 14.1 GBTTFT: fast
ollama run codegemma:7b
125
tok/s
Estimated
Weights
4.20 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Model details →
#11Turkish Gemma 9B T1
9B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.8 GBHeadroom: 12.2 GBTTFT: fast
97
tok/s
Estimated
Weights
5.00 GB
KV cache
4.50 GB
Activations
0.26 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~188 ms (fast)
Model details →
#12YTU Turkish Gemma 9B v0.1
9.2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 12.7 GBHeadroom: 11.3 GBTTFT: fast
ollama run alibayram/turkish-gemma-9b-v0.1:latest
95
tok/s
Estimated
Weights
5.80 GB
KV cache
4.60 GB
Activations
0.30 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~192 ms (fast)
Model details →

Runs with tradeoffs
74 models

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

Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 20.0 GBHeadroom: 4.0 GBTTFT: fast
  • • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run qwen2.5:14b
55
tok/s
Estimated
Weights
10.50 GB
KV cache
7.00 GB
Activations
0.53 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~292 ms (fast)
Model details →
Hermes 3 Llama 3.1 70B
70B
hermes
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 52.8 GBHeadroom: 9.6 GBTTFT: noticeable
  • • Partial CPU offload: ~55% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run hermes3:70b
1
tok/s
Estimated
Weights
40.00 GB
KV cache
8.75 GB
Activations
2.00 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~1459 ms (noticeable)
Model details →
Gemma 4 26B MoE
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.1 GBHeadroom: 1.9 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.9 GB headroom left for context growth
ollama run gemma4:26b-moe
34
tok/s
Estimated
Weights
16.00 GB
KV cache
3.25 GB
Activations
0.80 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~542 ms (noticeable)
Model details →
Gemma 4 26B-A4B
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.1 GBHeadroom: 1.9 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.9 GB headroom left for context growth
ollama run gemma4:26b-a4b-it-q4_K_M
34
tok/s
Estimated
Weights
16.00 GB
KV cache
3.25 GB
Activations
0.80 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~542 ms (noticeable)
Model details →
Gemma 4 Turkish 26B (4B active)
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 20.3 GBHeadroom: 3.7 GBTTFT: noticeable
  • • Tight VRAM fit — only 3.7 GB headroom left for context growth
34
tok/s
Estimated
Weights
14.30 GB
KV cache
3.25 GB
Activations
0.72 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~542 ms (noticeable)
Model details →
Gemma 3 27B
27B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.2 GBHeadroom: 1.8 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.8 GB headroom left for context growth
ollama run gemma3:27b
32
tok/s
Estimated
Weights
16.00 GB
KV cache
3.38 GB
Activations
0.80 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~563 ms (noticeable)
Model details →
MedGemma 27B
27B
gemma
Quant: Q4_K_MContext: 2,048VRAM: 22.2 GBHeadroom: 1.8 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.8 GB headroom left for context growth
32
tok/s
Estimated
Weights
16.00 GB
KV cache
3.38 GB
Activations
0.80 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~563 ms (noticeable)
Model details →
Llama 3.2 11B Vision Instruct
11B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 20.6 GBHeadroom: 3.4 GBTTFT: fast
  • • Tight VRAM fit — only 3.4 GB headroom left for context growth
ollama run llama3.2-vision:11b
45
tok/s
Estimated
Weights
12.50 GB
KV cache
5.50 GB
Activations
0.63 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~229 ms (fast)
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: 23 new comfortable, 80 new tradeoff

  • • Qwen 3 0.6B
  • • Gemma 3 270M
  • • SmolLM2 135M Instruct
  • • TinyLlama 1.1B Chat v1.0
Shop this upgrade↗

Upgrade to AMD Instinct MI210

see current pricing

64 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~960 GB/s to ~1638 GB/s.

Unlocks: 94 new comfortable

  • • Qwen 3 0.6B
  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen3.6 27B
Shop this upgrade↗

Add a second AMD Radeon RX 7900 XTX

~$899

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: 76 new comfortable

  • • Qwen 3 0.6B
  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen3.6 27B
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 (24 GB) + 60% of system RAM (38 GB) combined.

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

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

—
Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

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

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

—
Llama 4 Scout
109B
llama
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 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.