Beelink GTR9 Pro Ryzen AI Max+ 395 128GB
128 GB unified · 256 GB/s
In short
The Beelink GTR9 Pro Ryzen AI Max+ 395 128GB has 128 GB of unified memory, of which the GPU can use 96 GB by default, with 256 GB/s of memory bandwidth. At 128k context it runs 67 of the 113 open models we track fully in memory; the most capable is Qwen 3.8 Flash Next at UD-Q3_K_XL, at about 3 tok/s (estimated). We have no current price for the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB 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 it runs
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 | 88.5 GB | 256k | 3tok/sest. | 146 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 36.7 GB | 256k | 4tok/sest. | 256 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q5_K_M | fits | 89.9 GB | 256k | 8tok/sest. | 454 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 36.3 GB | 256k | 4tok/sest. | 256 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 83.6 GB | 256k | 11tok/sest. | 1008 tok/s | chat |
| gpt-oss 120B OpenAI | MXFP4 | fits | 65.1 GB | 128k | 11tok/sest. | 674 tok/s | chat |
| Nemotron 3 Super 120B-A12B NVIDIA | Q5_K_M | fits | 92.7 GB | 256k | 8tok/sest. | 638 tok/s | – |
| Gemma 4 31B | Q8_0 | fits | 42.7 GB | 256k | 3tok/sest. | 243 tok/s | – |
| Mistral Small 4 119B Mistral AI | Q6_K | fits | 95.3 GB | 152k241k with q8 cache | 10tok/sest. | 394 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 38.5 GB | 256k | 15tok/sest. | 1242 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 36.3 GB | 256k | 4tok/sest. | 256 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.3 GB | 256k | 12tok/sest. | 1508 tok/s | chat |
| GLM 4.5 Air Z.ai | Q4_K_M | fits | 92.5 GB | 128k | 2tok/sest. | 114 tok/s | – |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 38.5 GB | 256k | 15tok/sest. | 1242 tok/s | chat, coding |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 83.6 GB | 256k | 13tok/sest. | 1101 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 37.8 GB | 198k | 7tok/sest. | 586 tok/s | – |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 44.9 GB | 384k | 3tok/sest. | 229 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.9 GB | 256k | 20tok/sest. | 1671 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 51.2 GB | 1024k | 20tok/sest. | 932 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 15.8 GB | 128k | 15tok/sest. | 976 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 43.8 GB | 256k | 5tok/sest. | 361 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 66.0 GB | 40k | 2tok/sest. | 102 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 15.7 GB | 256k | 9tok/sest. | 627 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.5 GB | 256k | 10tok/sest. | 745 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 38.7 GB | 128k | 4tok/sest. | 313 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 44.9 GB | 128k | 3tok/sest. | 229 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 66.0 GB | 128k | 2tok/sest. | 137 tok/s | – |
| Llama 3.3 70B Meta | Q5_K_M | fits | 88.1 GB | 128k | 2tok/sest. | 66 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 34.9 GB | 256k | 4tok/sest. | 294 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 36.2 GB | 40k | 4tok/sest. | 250 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 27.7 GB | 128k | 5tok/sest. | 378 tok/s | – |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 27.7 GB | 40k | 5tok/sest. | 378 tok/s | – |
| Phi-4 14B Microsoft | Q8_0 | fits | 41.1 GB | 16k | 3tok/sest. | 251 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.8 GB | 256k | 16tok/sest. | 1161 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 27.0 GB | 256k | 5tok/sest. | 383 tok/s | – |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.3 GB | 128k | 5tok/sest. | 343 tok/s | – |
| Gemma 4 E4B | Q8_0 | fits | 12.7 GB | 128k | 12tok/sest. | 1045 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 15.9 GB | 125k | 11tok/sest. | 1397 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 23.7 GB | 128k | 6tok/sest. | 412 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 3.5 GB | 32k | 66tok/sest. | 3138 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.8 GB | 256k | 58tok/sest. | 4185 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.4 GB | 256k | 46tok/sest. | 2676 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 6.8 GB | 128k | 25tok/sest. | 1402 tok/s | chat, coding, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 15.4 GB | 128k | 18tok/sest. | 1616 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.3 GB | 128k | 17tok/sest. | 754 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 11.7 GB | 128k | 13tok/sest. | 967 tok/s | chat, coding |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 11.7 GB | 32k | 13tok/sest. | 930 tok/s | chat, coding |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 21.2 GB | 128k | 12tok/sest. | 1014 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 21.9 GB | 128k | 12tok/sest. | 1014 tok/s | chat |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 14.2 GB | 32k | 10tok/sest. | 337 tok/s | chat |
| granite vision 4.1 4b IBM | Q8_0 | fits | 14.9 GB | 128k | 10tok/sest. | 597 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 15.2 GB | 128k | 10tok/sest. | 609 tok/s | chat, coding |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 15.9 GB | 128k | 9tok/sest. | 327 tok/s | – |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 16.1 GB | 128k | 9tok/sest. | 501 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 17.5 GB | 64k | 8tok/sest. | 327 tok/s | – |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 35.3 GB | 128k | 7tok/sest. | 816 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 25.5 GB | 128k | 6tok/sest. | 412 tok/s | – |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 27.0 GB | 256k | 5tok/sest. | 383 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 40.2 GB | 128k | 3tok/sest. | 221 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 44.9 GB | 128k | 3tok/sest. | 231 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 44.9 GB | 40k | 3tok/sest. | 231 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 44.9 GB | 40k | 3tok/sest. | 231 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 44.9 GB | 128k | 3tok/sest. | 229 tok/s | – |
| GLM 4.5V Z.ai | Q4_K_M | fits | 83.8 GB | 64k | 3tok/sest. | 118 tok/s | – |
| GLM 4.6V Z.ai | Q4_K_M | fits | 90.2 GB | 128k | 3tok/sest. | 118 tok/s | – |
| granite 4.2 30b IBM | Q8_0 | fits | 62.5 GB | 128k | 2tok/sest. | 163 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q5_K_M | fits | 88.1 GB | 128k | 2tok/sest. | 66 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 102.5 GB | 55k99k with q8 cache | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.3 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 102.7 GB | 101k186k with q8 cache | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 386.8 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 386.8 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 386.8 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 387.7 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 387.7 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 387.7 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 157.9 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 166.7 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 115.3 GB | 72k135k with q8 cache | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 248.3 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 249.1 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 432.5 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 446.4 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 758.8 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 101.5 GB | 110k128k with q8 cache | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 588.3 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 588.7 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 588.7 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 588.7 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 161.4 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 161.4 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 147.8 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 263.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 115.3 GB | 72k135k with q8 cache | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
Compare with
Questions
- How much memory does the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB have for AI models?
- The Beelink GTR9 Pro Ryzen AI Max+ 395 128GB has 128 GB of unified memory, of which the GPU can use 96 GB by default, with 256 GB/s of memory bandwidth.
- What is the best model the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB can run locally?
- Qwen 3.8 Flash Next (UD-Q3_K_XL) fits fully in its memory at 128k context and generates at about 3 tok/s, an estimate from its memory bandwidth. 67 of the 113 models we track fit at that context.
- Can the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 102 GB at 128k context, more than the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB and system RAM can hold.
- How much does the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB cost in the US?
- We have no current price for the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB in the US.
Speeds on this page are for 128k context. See the best hardware for local AI at every budget.