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 64k context it runs 80 of the 129 open models we track fully in memory; the most capable is DeepSeek V4 Flash at UD-Q2_K_XL, at about 8 tok/s (estimated). We have no current price for the Lenovo ThinkStation PGX GB10 128GB in the UK.
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the UK, 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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | fits | 96.6 GB | 312k557k with q8 cache | 8tok/sest. | 124 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | fits | 103.1 GB | 1018k1024k with q8 cache | 11tok/sest. | 189 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | Q4_K_M | fits | 114.1 GB | 232k256k with q8 cache | 2tok/sest. | 210 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 32.3 GB | 256k | 5tok/sest. | 408 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q3_K_M | fits | 110.9 GB | 96k178k with q8 cache | 5tok/sest. | 388 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q6_K | fits | 96.8 GB | 256k | 10tok/sest. | 848 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 31.8 GB | 256k | 5tok/sest. | 408 tok/s | – |
| gpt-oss 120B OpenAI | MXFP4 | fits | 62.4 GB | 128k | 18tok/sest. | 1316 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 81.6 GB | 256k | 18tok/sest. | 1966 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q6_K | fits | 108.6 GB | 256k | 9tok/sest. | 986 tok/s | – |
| Gemma 4 31B | Q8_0 | fits | 37.3 GB | 256k | 4tok/sest. | 372 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q6_K | fits | 95.1 GB | 923k1024k with q8 cache | 14tok/sest. | 834 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 23tok/sest. | 2454 tok/s | chat, coding, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 31.8 GB | 256k | 5tok/sest. | 408 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.5 GB | 256k | 18tok/sest. | 2513 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q6_K | fits | 104.8 GB | 128k | 4tok/sest. | 276 tok/s | – |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 23tok/sest. | 2454 tok/s | chat, coding, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 81.6 GB | 256k | 21tok/sest. | 2242 tok/s | chat, coding, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 34.0 GB | 198k | 12tok/sest. | 1217 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 34.4 GB | 384k | 5tok/sest. | 402 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.1 GB | 256k | 27tok/sest. | 3026 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 50.3 GB | 1024k | 27tok/sest. | 1971 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.9 GB | 128k | 25tok/sest. | 1878 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.3 GB | 256k | 11tok/sest. | 878 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 49.5 GB | 40k | 3tok/sest. | 208 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 14.2 GB | 256k | 12tok/sest. | 966 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.0 GB | 256k | 14tok/sest. | 1182 tok/s | chat |
| Gemma 3 27B | Q8_0 | fits | 33.2 GB | 128k | 5tok/sest. | 457 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 34.4 GB | 128k | 5tok/sest. | 402 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 49.5 GB | 128k | 3tok/sest. | 257 tok/s | – |
| Llama 3.3 70B Meta | Q8_0 | fits | 90.9 GB | 128k | 2tok/sest. | 123 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.4 GB | 256k | 7tok/sest. | 565 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 25.7 GB | 40k | 6tok/sest. | 495 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.2 GB | 128k | 9tok/sest. | 781 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.2 GB | 40k | 9tok/sest. | 781 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.1 GB | 16k | 6tok/sest. | 497 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.3 GB | 256k | 25tok/sest. | 2049 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.0 GB | 256k | 9tok/sest. | 773 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 19.8 GB | 128k | 8tok/sest. | 714 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 10.5 GB | 128k | 17tok/sest. | 1548 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.5 GB | 125k | 24tok/sest. | 3305 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 15.2 GB | 128k | 11tok/sest. | 839 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.3 GB | 32k | 127tok/sest. | 7329 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.6 GB | 256k | 104tok/sest. | 8310 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.2 GB | 256k | 75tok/sest. | 4530 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 3.6 GB | 256k | 64tok/sest. | 5464 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 4.6 GB | 128k | 45tok/sest. | 3036 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.2 GB | 128k | 31tok/sest. | 1711 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.2 GB | 1024k | 31tok/sest. | 2101 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.0 GB | 128k | 28tok/sest. | 3062 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 7.4 GB | 256k | 25tok/sest. | 2049 tok/s | chat, coding, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.5 GB | 128k | 25tok/sest. | 2075 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.5 GB | 32k | 25tok/sest. | 1951 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 18.8 GB | 128k | 20tok/sest. | 2106 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 19.6 GB | 128k | 19tok/sest. | 1654 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.4 GB | 128k | 19tok/sest. | 1303 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 9.7 GB | 128k | 18tok/sest. | 1345 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 11.0 GB | 256k | 16tok/sest. | 1288 tok/s | chat, coding |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 11.3 GB | 32k | 16tok/sest. | 693 tok/s | chat |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.1 GB | 128k | 14tok/sest. | 983 tok/s | chat |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 29.8 GB | 128k | 14tok/sest. | 1893 tok/s | chat, coding |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 12.9 GB | 128k | 13tok/sest. | 663 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 14.5 GB | 64k | 12tok/sest. | 663 tok/s | – |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.0 GB | 128k | 10tok/sest. | 839 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.0 GB | 256k | 9tok/sest. | 773 tok/s | chat |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 24.4 GB | 256k | 7tok/sest. | 565 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 24.5 GB | 256k | 7tok/sest. | 408 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 27.7 GB | 128k | 6tok/sest. | 452 tok/s | – |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 32.1 GB | 128k | 5tok/sest. | 411 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 34.4 GB | 128k | 5tok/sest. | 407 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 34.4 GB | 40k | 5tok/sest. | 407 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 34.4 GB | 40k | 5tok/sest. | 407 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 34.4 GB | 128k | 5tok/sest. | 402 tok/s | – |
| GLM 4.5V Z.ai | Q8_0 | fits | 118.4 GB | 64k | 4tok/sest. | 272 tok/s | – |
| GLM 4.6V Z.ai | Q8_0 | fits | 118.4 GB | 67k123k with q8 cache | 4tok/sest. | 272 tok/s | – |
| granite 4.2 30b IBM | Q8_0 | fits | 46.1 GB | 128k | 4tok/sest. | 300 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 90.9 GB | 128k | 2tok/sest. | 123 tok/s | – |
| Kimi Dev 72B Moonshot AI | Q8_0 | fits | 93.0 GB | 128k | 2tok/sest. | 121 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q6_K | fits | 118.6 GB | 65k120k with q8 cache | 1tok/sest. | 71 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q6_K | fits | 118.6 GB | 65k120k with q8 cache | 1tok/sest. | 70 tok/s | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.5 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 160.9 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 224.9 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 388.9 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.5 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.4 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 752.9 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.5 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 131.8 GB | 12k22k with q8 cache | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.3 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 64k context and generates at about 8 tok/s, an estimate from its memory bandwidth. 80 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 382 GB at 64k 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 the UK?
- We have no current price for the Lenovo ThinkStation PGX GB10 128GB in the UK.
Speeds on this page are for 64k context. See the best hardware for local AI at every budget.