Radeon PRO W7900 Price & Used Prices: Which Local LLMs Can It Run?
The Radeon PRO W7900 has 48GB of GDDR6 ECC memory with 864 GB/s of bandwidth. No price data yet. At Q4 quantization it runs models up to 70B parameters at roughly 10 tokens/s.
Radeon PRO W7900 price history
AmazonJP
Full Radeon PRO W7900 specifications
What LLMs can the Radeon PRO W7900 run?
Versions released since 2026 with up to 50B parameters| Model | 2-bit | 4-bit | 8-bit | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Fits | Speed t/s | Context | Fits | Speed t/s | Context | Fits | Speed t/s | Context | |
| GemmaGemma 4 E4B | ✓ | 116.3 | 128K | ✓ | 82.5 | 128K | ✓ | 47.2 | 128K |
| QwenQwen3.5 9B | ✓ | 95.7 | 128K | ✓ | 68.1 | 128K | ✓ | 39 | 128K |
| GemmaGemma 4 12B | ✓ | 67.6 | 32K | ✓ | 49.9 | 32K | ✓ | 29.7 | 32K |
| GemmaGemma 4 26B A4B | ✓ | 103.2 | 128K | ✓ | 87.4 | 128K | ✓ | 62.6 | 32K |
| QwenQwen3.6 27B | ✓ | 36.3 | 128K | ✓ | 25.1 | 32K | ✓ | 14 | 32K |
| QwenQwen3.8 27B | ✓ | 36.3 | 128K | ✓ | 25.1 | 32K | ✓ | 14 | 32K |
| GLMGLM 4.7 Flash | ✓ | 140.5 | 128K | ✓ | 118.5 | 128K | ✓ | 84.5 | 128K |
| GemmaGemma 4 31B | ✓ | 27 | 32K | ✓ | 19.7 | 8K | ✓ | 11.6 | 8K |
| QwenQwen3.6 35B A3B | ✓ | 135.8 | 128K | ✓ | 115.2 | 128K | ✓ | 82.8 | 32K |
Fits when weights + KV cache + runtime overhead is at or below usable memory, single card. "Offload" on MoE models means it runs with expert weights in system RAM (only attention layers and KV cache stay in VRAM); that speed assumes 70 GB/s RAM bandwidth. The context column is the largest tier that fits.
Prices by platform
Buy links may carry affiliate tags; they do not change the price you pay.
FAQ
How much VRAM does the Radeon PRO W7900 have?
The Radeon PRO W7900 has 48GB of GDDR6 ECC memory with 864 GB/s of bandwidth.
Can the Radeon PRO W7900 run a 70B model?
Yes. At Q4_K_M with an 8K context a 70B dense model needs about 43GB, which fits in the Radeon PRO W7900's 48GB.
How much does a Radeon PRO W7900 cost?
No price data yet; it will appear here once the feed is live.