Products · AMD · Workstation card
AMD Radeon PRO W7900
- GPU
- AMD Radeon PRO W7900
- VRAM
- 48 GB
- Launch price
- $3,999
- Released
- 2023
Specifications
| Maker | AMD |
|---|---|
| Type | Workstation card |
| GPU | AMD Radeon PRO W7900 |
| Video memory (VRAM) | 48.0 GB |
| Usable for AI models | 48.0 GB |
| Memory bandwidth | 864 GB/s |
| FP16 compute | 122.6 TFLOPS |
| Notes | Triple-slot, 295 W, ECC |
| Product page | www.amd.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 AMD Radeon PRO W7900
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q8_0 | 40.5 GB | 97.5 tok/s | Runs great |
| 92Excellent quality (A+) · 92 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. | Qwen3.6 35B-A3B | Q6_K | 32.6 GB | 120 tok/s | Runs great |
| 92Excellent quality (A+) · 92 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. | Qwen3.5 35B-A3B | Q6_K | 32.6 GB | 120 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | Q8_0 | 30.8 GB | 83.5 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q8_0 | 40.4 GB | 97.5 tok/s | Runs great |
| 91Excellent quality (A+) · 91 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. | KAT-Coder V2.5 Dev (35B-A3B) | Q8_0 | 39.9 GB | 97.5 tok/s | Runs great |
| 90Excellent quality (A+) · 90 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. | Sage-A1.5 35B-A3B | Q6_K | 32.6 GB | 120 tok/s | Runs great |
| 89Excellent quality (A+) · 89 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. | Flint (40B-A2.5B) | Q6_K | 35.9 GB | 132 tok/s | Runs great |
| 89Excellent quality (A+) · 89 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. | Ornith 1.5 35B-A3B | Q6_K | 32.6 GB | 120 tok/s | Runs great |
| 88Excellent quality (A+) · 88 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. | Apodex 1.1 Mini (35B-A3B) | Q6_K | 32.6 GB | 120 tok/s | Runs great |
Best Image models for the AMD Radeon PRO W7900
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 4.8 s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 Turbo | FP8 | 30.8 GB | 12 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. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 2.0 s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP16 | 22.4 GB | 6.4 s | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | FP16 | 26.4 GB | 3.6 s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 Image | FP8 | 38.6 GB | 11 s | Runs greatencoder in RAM |
Best Video models for the AMD Radeon PRO W7900
| 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 91/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | Q4 GGUF | 39.9 GB | 2.0 min | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | FP8 | 44.3 GB | 6.7 min | Runs welltight fit |
| 66Good quality (B) · 66 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. | LTX-Video 13B 0.9.8 (distilled) | FP8 | 30.1 GB | 60 s | Runs great |
| 80Great quality (A) · 80 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. | LTX-2 (19B, video + audio) | FP8 | 44.3 GB | 6.7 min | Runs welltight fit |
| 84Great quality (A) · 84 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. | Wan 2.2 I2V A14B | FP8 | 38.3 GB | 26.8 min | Slow |
Best Decision models for the AMD Radeon PRO W7900
| 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 | 11.3 GB | 50 ms | Runs great |
| 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 8B | F16 | 19.7 GB | 97 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 | 11.3 GB | 50 ms | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 114 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 27B | Q8_0 | 34.8 GB | 100 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 | 4.4 GB | 11 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 | 10.9 GB | 48 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. | Intern-Decision 4B | F16 | 12.1 GB | 40 ms | Runs great |
Other products with the AMD Radeon PRO W7900
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.