Lenovo ThinkStation PGX GB10 128GB
128 GB unified · 273 GB/s
In short
The Lenovo ThinkStation PGX GB10 128GB has 128 GB of unified memory, of which the GPU can use 119 GB by default, with 273 GB/s of memory bandwidth. At 8k context it runs 81 of the 129 open models we track fully in memory; the most capable is DeepSeek V4 Flash at UD-Q2_K_XL, at about 14 tok/s (estimated). We have no current price for the Lenovo ThinkStation PGX GB10 128GB in Germany.
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in Germany, 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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | fits | 91.6 GB | 312k557k with q8 cache | 14tok/sest. | 437 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | fits | 102.2 GB | 1018k1024k with q8 cache | 12tok/sest. | 444 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | Q4_K_M | fits | 112.4 GB | 232k256k with q8 cache | 3tok/sest. | 224 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q3_K_M | fits | 97.0 GB | 96k178k with q8 cache | 15tok/sest. | 986 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 6tok/sest. | 488 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q6_K | fits | 95.1 GB | 256k | 12tok/sest. | 1291 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 256k | 6tok/sest. | 488 tok/s | – |
| gpt-oss 120B OpenAI | MXFP4 | fits | 60.1 GB | 128k | 30tok/sest. | 2189 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 80.0 GB | 256k | 23tok/sest. | 3261 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q6_K | fits | 107.8 GB | 256k | 9tok/sest. | 1137 tok/s | – |
| Gemma 4 31B | Q8_0 | fits | 32.5 GB | 256k | 5tok/sest. | 426 tok/s | – |
| Mistral Small 4 119B Mistral AI | Q8_0 | fits | 118.7 GB | 18k29k with q8 cache | 13tok/sest. | 1687 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.3 GB | 256k | 31tok/sest. | 4182 tok/s | chat, coding, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 256k | 6tok/sest. | 488 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.1 GB | 256k | 22tok/sest. | 3187 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q8_0 | fits | 111.6 GB | 48k87k with q8 cache | 6tok/sest. | 769 tok/s | – |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.3 GB | 256k | 31tok/sest. | 4182 tok/s | chat, coding, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 80.0 GB | 256k | 30tok/sest. | 4100 tok/s | chat, coding, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 30.8 GB | 198k | 18tok/sest. | 2341 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.3 GB | 384k | 6tok/sest. | 550 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.4 GB | 256k | 30tok/sest. | 4358 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.2 GB | 128k | 39tok/sest. | 3027 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 49.5 GB | 1024k | 31tok/sest. | 3975 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 31.7 GB | 256k | 25tok/sest. | 3026 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.2 GB | 40k | 5tok/sest. | 376 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.0 GB | 256k | 13tok/sest. | 1110 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 9.9 GB | 256k | 17tok/sest. | 1406 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 6tok/sest. | 550 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 28.5 GB | 128k | 6tok/sest. | 495 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.2 GB | 128k | 5tok/sest. | 394 tok/s | – |
| Llama 3.3 70B Meta | Q8_0 | fits | 73.1 GB | 128k | 2tok/sest. | 184 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.4 GB | 256k | 11tok/sest. | 913 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.6 GB | 40k | 10tok/sest. | 848 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.0 GB | 128k | 17tok/sest. | 1484 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 40k | 17tok/sest. | 1484 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.8 GB | 16k | 10tok/sest. | 854 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.2 GB | 256k | 35tok/sest. | 2831 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.2 GB | 256k | 17tok/sest. | 1387 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.7 GB | 128k | 16tok/sest. | 1377 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 8.6 GB | 128k | 20tok/sest. | 1704 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.5 GB | 125k | 69tok/sest. | 9945 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 7.9 GB | 128k | 22tok/sest. | 1532 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.3 GB | 32k | 268tok/sest. | 20815 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.6 GB | 256k | 182tok/sest. | 14321 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.2 GB | 256k | 109tok/sest. | 5874 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 2.6 GB | 256k | 87tok/sest. | 7547 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.7 GB | 128k | 80tok/sest. | 6551 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.6 GB | 128k | 56tok/sest. | 4330 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 3.9 GB | 128k | 50tok/sest. | 4359 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 3.9 GB | 32k | 50tok/sest. | 3846 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 3.9 GB | 1024k | 50tok/sest. | 3081 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.7 GB | 128k | 39tok/sest. | 2885 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 5.0 GB | 256k | 37tok/sest. | 2955 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 5.0 GB | 128k | 37tok/sest. | 3101 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 25.1 GB | 128k | 36tok/sest. | 5223 tok/s | chat, coding |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 12.9 GB | 128k | 36tok/sest. | 4792 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 5.3 GB | 256k | 34tok/sest. | 2831 tok/s | chat, coding, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 16.8 GB | 128k | 30tok/sest. | 4040 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 17.6 GB | 128k | 29tok/sest. | 3791 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.7 GB | 128k | 20tok/sest. | 1653 tok/s | chat |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 8.7 GB | 32k | 20tok/sest. | 1299 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.7 GB | 128k | 18tok/sest. | 1532 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.2 GB | 256k | 17tok/sest. | 1387 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.4 GB | 128k | 16tok/sest. | 1199 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.0 GB | 64k | 14tok/sest. | 1199 tok/s | – |
| MiniMax M2.5 MiniMax | MXFP4 | fits | 118.0 GB | 12k22k with q8 cache | 13tok/sest. | 985 tok/s | – |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 15.4 GB | 256k | 11tok/sest. | 913 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 16.9 GB | 128k | 10tok/sest. | 831 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 20.6 GB | 256k | 8tok/sest. | 488 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 6tok/sest. | 560 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 25.3 GB | 40k | 6tok/sest. | 560 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 25.3 GB | 40k | 6tok/sest. | 560 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 6tok/sest. | 550 tok/s | – |
| GLM 4.5V Z.ai | Q8_0 | fits | 108.0 GB | 64k | 6tok/sest. | 738 tok/s | – |
| GLM 4.6V Z.ai | Q8_0 | fits | 108.0 GB | 67k123k with q8 cache | 6tok/sest. | 738 tok/s | – |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 31.0 GB | 128k | 5tok/sest. | 452 tok/s | – |
| granite 4.2 30b IBM | Q8_0 | fits | 31.7 GB | 128k | 5tok/sest. | 444 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 73.1 GB | 128k | 2tok/sest. | 184 tok/s | – |
| Kimi Dev 72B Moonshot AI | Q8_0 | fits | 75.2 GB | 128k | 2tok/sest. | 179 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q6_K | fits | 99.0 GB | 65k120k with q8 cache | 2tok/sest. | 104 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q6_K | fits | 99.0 GB | 65k120k with q8 cache | 2tok/sest. | 102 tok/s | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.4 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 155.8 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 205.2 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 204.4 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.2 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 383.8 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 747.8 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.4 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 241.4 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
Compare with
Questions
- How much memory does the Lenovo ThinkStation PGX GB10 128GB have for AI models?
- The Lenovo ThinkStation PGX GB10 128GB has 128 GB of unified memory, of which the GPU can use 119 GB by default, with 273 GB/s of memory bandwidth.
- What is the best model the Lenovo ThinkStation PGX GB10 128GB can run locally?
- DeepSeek V4 Flash (UD-Q2_K_XL) fits fully in its memory at 8k context and generates at about 14 tok/s, an estimate from its memory bandwidth. 81 of the 129 models we track fit at that context.
- Can the Lenovo ThinkStation PGX GB10 128GB run DeepSeek R1?
- No: even at Q4_K_M, DeepSeek R1 needs about 378 GB at 8k context, more than the Lenovo ThinkStation PGX GB10 128GB and system RAM can hold.
- How much does the Lenovo ThinkStation PGX GB10 128GB cost in Germany?
- We have no current price for the Lenovo ThinkStation PGX GB10 128GB in Germany.
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.