Products · Lenovo · Workstation
Lenovo ThinkStation P620 Tower Workstation
- Chips
- 14 GPU options, from NVIDIA T400 to NVIDIA RTX 6000 Ada Generation
- VRAM
- 4, 8, 12, 16, 20, 24 or 48 GB
- Released
- 2024
Configurations
Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.
| Configuration | Memory | Usable for AI | Bandwidth | LLMs that run well | Launch price |
|---|---|---|---|---|---|
| NVIDIA T400 | 4.0 GB | 4.0 GB | 80 GB/s | 215 of 622 | — |
| NVIDIA Quadro RTX 4000 | 8.0 GB | 8.0 GB | 416 GB/s | 338 of 622 | — |
| NVIDIA T1000 8GB | 8.0 GB | 8.0 GB | 160 GB/s | 338 of 622 | — |
| NVIDIA RTX A2000 12GB | 12.0 GB | 12.0 GB | 288 GB/s | 421 of 622 | — |
| NVIDIA Quadro RTX 5000 | 16.0 GB | 16.0 GB | 448 GB/s | 460 of 622 | — |
| NVIDIA RTX A4000 | 16.0 GB | 16.0 GB | 448 GB/s | 460 of 622 | — |
| NVIDIA RTX 2000 Ada Generation | 16.0 GB | 16.0 GB | 224 GB/s | 455 of 622 | — |
| NVIDIA RTX A4500 | 20.0 GB | 20.0 GB | 640 GB/s | 461 of 622 | — |
| NVIDIA RTX 4000 Ada Generation | 20.0 GB | 20.0 GB | 360 GB/s | 461 of 622 | — |
| NVIDIA Quadro RTX 6000 | 24.0 GB | 24.0 GB | 672 GB/s | 466 of 622 | — |
| NVIDIA RTX A5000 | 24.0 GB | 24.0 GB | 768 GB/s | 466 of 622 | — |
| NVIDIA Quadro RTX 8000 | 48.0 GB | 48.0 GB | 672 GB/s | 516 of 622 | — |
| NVIDIA RTX A6000 | 48.0 GB | 48.0 GB | 768 GB/s | 516 of 622 | — |
| NVIDIA RTX 6000 Ada Generation | 48.0 GB | 48.0 GB | 960 GB/s | 517 of 622 | — |
Specifications 8.0 GB configuration
| Maker | Lenovo |
|---|---|
| Type | Workstation |
| Chip | NVIDIA Quadro RTX 4000 |
| Video memory (VRAM) | 8.0 GB |
| Usable for AI models | 8.0 GB |
| Memory bandwidth | 416 GB/s |
| FP16 compute | 7.1 TFLOPS |
| Notes | Workstation with NVIDIA RTX professional graphics; each option below is a GPU you can configure. Listed on the NVIDIA Marketplace. |
| Product page | www.lenovo.com (opens in a new tab) |
Best LLMs for the Lenovo ThinkStation P620 Tower Workstation 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | K2 Horizon 7B | Q4_K_M | 7.7 GB | 56.7 tok/s | Runs welltight fit |
| 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.6 Distill Qwen 9B | Q5_K_M | 7.9 GB | 44.8 tok/s | Runs welltight fit |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova Loop 9B Preview | Q4_K_M | 7.4 GB | 52.9 tok/s | Runs welltight fit |
| 73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 9B | Q4_K_M | 7.2 GB | 52.9 tok/s | Runs welltight fit |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | TMax 9B | Q4_K_M | 6.7 GB | 57.1 tok/s | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 9B | Q4_K_M | 7.2 GB | 52.9 tok/s | Runs welltight fit |
| 71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 9B | Q4_K_M | 7.2 GB | 52.9 tok/s | Runs welltight fit |
| 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Labs Dory 1.0 4B | Q8_0 | 5.7 GB | 65.3 tok/s | Runs great |
| 69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 12B | Q3_K_M | 7.5 GB | 55.2 tok/s | Runs welltight fit |
| 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.2 3B | Q6_K | 5.9 GB | 85.0 tok/s | Runs great |
Best Image models for the Lenovo ThinkStation P620 Tower Workstation 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | Q8 GGUF | 6.4 GB | 7.6 s | Runs greatencoder in RAM |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | Q4 GGUF | 6.1 GB | 20 s | Runs wellencoder in RAM |
| 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper XL v2 Turbo | FP8 | 5.6 GB | 7.4 s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q4 GGUF | 5.7 GB | 45 s | Slowencoder in RAM |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | SDXL-Lightning (4-step) | FP8 | 5.6 GB | 4.0 s | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | Q4 GGUF | 7.4 GB | 25 s | Runs welltight fit · encoder in RAM |
Best Video models for the Lenovo ThinkStation P620 Tower Workstation 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 6.1 GB | 2.5 min | Runs greatencoder in RAM |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 2.1 min | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 2B | FP8 | 6.2 GB | 6.0 min | Runs wellencoder in RAM |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 1.3B | FP8 | 7.1 GB | 23.8 min | Slowtight fit · encoder in RAM |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B | FP8 | 5.9 GB | 22.1 min | SlowCPU offload |
Best Decision models for the Lenovo ThinkStation P620 Tower Workstation 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | F16 | 2.4 GB | 69 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | F16 | 2.4 GB | 69 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | F16 | 2.4 GB | 55 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | F16 | 1.7 GB | 35 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 0.6B | F16 | 2.4 GB | 69 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | F16 | 1.2 GB | 39 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-base v2 | F16 | 2.0 GB | 57 ms | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q8_0 | 2.7 GB | 164 ms | Runs well |
Spec sources
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.