AMD Radeon PRO W7900
48 GB · 864 GB/s · 295 W
In short
The AMD Radeon PRO W7900 has 48 GB of GDDR6 memory with 864 GB/s of bandwidth, which sets how fast it generates text. At 128k context it runs 73 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 Flash Next at UD-Q3_K_XL, at about 8 tok/s (estimated). We have no current price for the AMD Radeon PRO W7900 in the US.
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What two of them run
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q3_K_XL | fits | 89.0 GB | 256k | 8tok/sest. | 301 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 13tok/sest. | 528 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q5_K_M | fits | 90.4 GB | 256k | 27tok/sest. | 938 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 13tok/sest. | 528 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 84.1 GB | 256k | 38tok/sest. | 2080 tok/s | chat, coding, agents, long documents |
| gpt-oss 120B OpenAI | MXFP4 | fits | 65.6 GB | 128k | 36tok/sest. | 1390 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | Q5_K_M | fits | 93.2 GB | 217k256k with q8 cache | 27tok/sest. | 1317 tok/s | chat, coding, long documents |
| Gemma 4 31B | Q8_0 | fits | 43.2 GB | 256k | 11tok/sest. | 501 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q5_K_M | fits | 87.9 GB | 361k573k with q8 cache | 34tok/sest. | 813 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 39.0 GB | 256k | 49tok/sest. | 2564 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 13tok/sest. | 528 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.8 GB | 256k | 40tok/sest. | 3112 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q4_K_M | fits | 93.0 GB | 128k | 8tok/sest. | 245 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 39.0 GB | 256k | 49tok/sest. | 2564 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 84.1 GB | 256k | 44tok/sest. | 2272 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 38.3 GB | 198k | 23tok/sest. | 1209 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 45.4 GB | 384k | 10tok/sest. | 472 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 35.4 GB | 256k | 68tok/sest. | 3449 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 51.7 GB | 1024k | 67tok/sest. | 1924 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 16.3 GB | 128k | 50tok/sest. | 2015 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 44.3 GB | 256k | 18tok/sest. | 746 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 66.5 GB | 40k | 7tok/sest. | 211 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 16.2 GB | 256k | 31tok/sest. | 1293 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 15.0 GB | 256k | 34tok/sest. | 1538 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 39.2 GB | 128k | 12tok/sest. | 646 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 45.4 GB | 128k | 10tok/sest. | 472 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 66.5 GB | 128k | 7tok/sest. | 283 tok/s | – |
| Llama 3.3 70B Meta | Q5_K_M | fits | 88.6 GB | 128k | 5tok/sest. | 137 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 35.4 GB | 256k | 13tok/sest. | 606 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 36.7 GB | 40k | 13tok/sest. | 516 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 28.2 GB | 128k | 17tok/sest. | 780 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 28.2 GB | 40k | 17tok/sest. | 780 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 41.6 GB | 16k | 11tok/sest. | 517 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 54tok/sest. | 2396 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 27.5 GB | 256k | 17tok/sest. | 790 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.8 GB | 128k | 15tok/sest. | 709 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 13.2 GB | 128k | 40tok/sest. | 2157 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 16.4 GB | 125k | 38tok/sest. | 2883 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 24.2 GB | 128k | 20tok/sest. | 851 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 4.0 GB | 32k | 222tok/sest. | 6477 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 4.3 GB | 256k | 195tok/sest. | 8637 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.9 GB | 256k | 155tok/sest. | 5523 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 7.3 GB | 128k | 84tok/sest. | 2894 tok/s | chat, coding, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 15.9 GB | 128k | 62tok/sest. | 3335 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 9.4 GB | 1024k | 60tok/sest. | 2369 tok/s | chat, coding, agents, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.8 GB | 128k | 57tok/sest. | 1556 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 10.4 GB | 256k | 53tok/sest. | 2396 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 12.2 GB | 128k | 44tok/sest. | 1996 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 12.2 GB | 32k | 44tok/sest. | 1920 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 21.7 GB | 128k | 40tok/sest. | 2094 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 22.4 GB | 128k | 39tok/sest. | 2094 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 14.7 GB | 32k | 35tok/sest. | 695 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 15.4 GB | 128k | 33tok/sest. | 1232 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 15.7 GB | 128k | 33tok/sest. | 1256 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 16.4 GB | 128k | 31tok/sest. | 675 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 16.6 GB | 128k | 30tok/sest. | 1033 tok/s | chat, coding, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 18.0 GB | 64k | 28tok/sest. | 675 tok/s | chat, coding, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 18.5 GB | 256k | 27tok/sest. | 1205 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 35.8 GB | 128k | 22tok/sest. | 1684 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 26.0 GB | 128k | 19tok/sest. | 851 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 27.5 GB | 256k | 17tok/sest. | 790 tok/s | chat, coding, agents, long documents |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 29.4 GB | 256k | 16tok/sest. | 528 tok/s | chat, coding, long documents |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 33.9 GB | 128k | 14tok/sest. | 574 tok/s | – |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 35.4 GB | 256k | 13tok/sest. | 606 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 40.7 GB | 128k | 12tok/sest. | 457 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 45.4 GB | 128k | 10tok/sest. | 476 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 45.4 GB | 40k | 10tok/sest. | 476 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 45.4 GB | 40k | 10tok/sest. | 476 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 45.4 GB | 128k | 10tok/sest. | 472 tok/s | chat |
| GLM 4.5V Z.ai | Q4_K_M | fits | 84.3 GB | 64k | 9tok/sest. | 243 tok/s | chat |
| GLM 4.6V Z.ai | Q4_K_M | fits | 90.7 GB | 128k | 8tok/sest. | 243 tok/s | chat |
| granite 4.2 30b IBM | Q8_0 | fits | 63.0 GB | 128k | 7tok/sest. | 337 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q5_K_M | fits | 88.6 GB | 128k | 5tok/sest. | 137 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | offload | 103.0 GB | 32k57k with q8 cache | 9tok/sest. | 99 tok/s | chat, coding |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | offload | 104.8 GB | – | 16tok/sest. | 165 tok/s | chat |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | offload | 103.2 GB | 92k170k with q8 cache | 5tok/sest. | 334 tok/s | chat, coding |
| Kimi Dev 72B Moonshot AI | Q6_K | offload | 102.0 GB | 104k128k with q8 cache | 3tok/sest. | 129 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | offload | 115.8 GB | 66k123k with q8 cache | 2tok/sest. | 71 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | offload | 115.8 GB | 66k123k with q8 cache | 2tok/sest. | 71 tok/s | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.8 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 158.4 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 167.2 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 249.6 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 248.8 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 249.6 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 395.4 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 433.0 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 446.9 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 759.3 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 588.8 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 161.9 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 161.9 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 148.3 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 256.7 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Radeon PRO W7900
- Memory
- 48 GB GDDR6
- Memory bus
- 384-bit
- Memory bandwidth
- 864 GB/s
- FP16 compute
- 122.6 TFLOPS
- Software
- ROCm
- Board power
- 295 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the AMD Radeon PRO W7900 have for AI models?
- The AMD Radeon PRO W7900 has 48 GB of GDDR6 memory with 864 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the AMD Radeon PRO W7900 can run locally?
- Qwen 3.8 Flash Next (UD-Q3_K_XL) fits fully in its memory at 128k context and generates at about 8 tok/s, an estimate from its memory bandwidth. 73 of the 125 models we track fit at that context.
- Can the AMD Radeon PRO W7900 run DeepSeek V4 Flash?
- Not fully in memory: at UD-Q2_K_XL and 128k context DeepSeek V4 Flash needs about 103 GB, so part of it runs from system RAM and it slows to about 9 tok/s (estimated).
- How much does the AMD Radeon PRO W7900 cost in the US?
- We have no current price for the AMD Radeon PRO W7900 in the US.
Speeds on this page are for 128k context. See the best hardware for local AI at every budget.