
Products · PowerColor · Workstation card
PowerColor Radeon AI PRO R9700
- GPU
- AMD Radeon AI PRO R9700
- VRAM
- 32 GB
- Reference MSRP
- $1,299
- Released
- 2025
Specifications
| Maker | PowerColor |
|---|---|
| Type | Workstation card |
| GPU | AMD Radeon AI PRO R9700 |
| Video memory (VRAM) | 32.0 GB |
| Usable for AI models | 32.0 GB |
| Memory bandwidth | 640 GB/s |
| FP16 compute | 95.7 TFLOPS |
| Notes | Blower reference-style design; a second PowerColor R9700 page exists (product-detail255.htm, likely revised version) |
| Product page | www.powercolor.com (opens in a new tab) |
Cards built on the same GPU with the same memory run AI models at practically the same speed; factory overclocks and coolers change results by only a few percent.
Best LLMs for the PowerColor Radeon AI PRO R9700
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | Q6_K | 23.8 GB | 85.4 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q6_K | 31.8 GB | 100 tok/s | Runs welltight fit |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q6_K | 31.2 GB | 100 tok/s | Runs welltight fit |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q6_K | 31.8 GB | 100 tok/s | Runs welltight fit |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q6_K | 31.2 GB | 100 tok/s | Runs welltight fit |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q5_K_M | 27.0 GB | 113 tok/s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | Q6_K | 31.8 GB | 100 tok/s | Runs welltight fit |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Raon-1 mini Preview (30B-A4B) | Q6_K | 25.9 GB | 78.3 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 35B-A3B | Q6_K | 31.8 GB | 100 tok/s | Runs welltight fit |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Apodex 1.1 Mini (35B-A3B) | Q6_K | 31.8 GB | 100 tok/s | Runs welltight fit |
Best Image models for the PowerColor Radeon AI PRO R9700
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP16 | 22.4 GB | 7.7 s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP8 | 20.2 GB | 5.2 s | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | FP16 | 26.4 GB | 4.3 s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | FP16 | 22.7 GB | 3.4 s | Runs great |
| 83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | Q8 GGUF | 20.5 GB | 2.8 s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 Turbo | FP8 | 30.8 GB | 14 s | Runs welltight fit |
Best Video models for the PowerColor Radeon AI PRO R9700
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | Q4 GGUF | 26.8 GB | 2.6 min | Runs greatencoder in RAM |
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP8 | 26.0 GB | 14.5 min | Slow |
| 66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 13B 0.9.8 (distilled) | FP8 | 30.1 GB | 73 s | Runs welltight fit |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP8 | 24.6 GB | 10.7 min | Runs well |
| 72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | FramePack I2V (HunyuanVideo 13B) | FP8 | 28.2 GB | 8.1 min | Runs welltight fit |
Best Decision models for the PowerColor Radeon AI PRO R9700
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | F16 | 10.5 GB | 64 ms | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q8_0 | 11.2 GB | 98 ms | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at F16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | F16 | 10.5 GB | 64 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | F16 | 3.6 GB | 13 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | F16 | 10.1 GB | 61 ms | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 145 ms | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Intern-Decision 4B | F16 | 11.3 GB | 52 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | F16 | 3.6 GB | 13 ms | Runs great |
Other products with the AMD Radeon AI PRO R9700
Spec sources
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

