Best LLMs for 48 GB VRAM
作者： Jakub Rusinowski · 最后更新： 2026年4月16日
These are the strongest local models that fit entirely in 48 GB of VRAM, ranked by capability, with the quantization level and estimated tokens/sec needed to fit.
GPUs at This Tier
Ranked Models
| Qwen 2.5 Family — Qwen 2.5 72B Instruct | Q4_K_M · 43.47 GB · ~19 tok/s on NVIDIA RTX 6000 Ada Generation |
| Qwen 2.5 Family — Qwen 2.5 Coder 32B | Q4_K_M · 19.32 GB · ~40 tok/s on NVIDIA RTX 6000 Ada Generation |
| Llama 3.3 — Llama 3.3 70B Instruct | Q2_K_XS (Tight) · 20.212500000000002 GB · ~38 tok/s on NVIDIA RTX 6000 Ada Generation |
| Qwen 3 — Qwen 3 32B | Q4_K_M · 19.802999999999997 GB · ~39 tok/s on NVIDIA RTX 6000 Ada Generation |
| DeepSeek R1 — DeepSeek R1 Distill Qwen 32B | Q4_K_M · 19.32 GB · ~40 tok/s on NVIDIA RTX 6000 Ada Generation |
| Qwen 2.5 Family — Qwen 2.5 14B Instruct | Q4_K_M · 8.4525 GB · ~79 tok/s on NVIDIA RTX 6000 Ada Generation |
| Nemotron 70B — Nemotron 70B Instruct | Q4_K_M · 42.62475 GB · ~19 tok/s on NVIDIA RTX 6000 Ada Generation |
| Qwen 3 — Qwen 3 14B | Q4_K_M · 8.935500000000001 GB · ~77 tok/s on NVIDIA RTX 6000 Ada Generation |
| Codestral — Codestral 22B | Q4_K_M · 13.40325 GB · ~54 tok/s on NVIDIA RTX 6000 Ada Generation |
| Qwen 3.6 — Qwen 3.6 35B-A3B | Q4_K_M · 21.13125 GB · ~187 tok/s on NVIDIA RTX 6000 Ada Generation |
| DeepSeek R1 — DeepSeek R1 Distill Qwen 14B | Q4_K_M · 8.4525 GB · ~80 tok/s on NVIDIA RTX 6000 Ada Generation |
| Phi-4 Family — Phi-4 (14B) | Q4_K_M · 8.4525 GB · ~79 tok/s on NVIDIA RTX 6000 Ada Generation |
| Gemma 4 — Gemma 4 31B | Q4_K_M · 18.71625 GB · ~41 tok/s on NVIDIA RTX 6000 Ada Generation |
| Qwen 2.5 VL — Qwen 2.5 VL 72B Instruct | Q4_K_M · 44.315250000000006 GB · ~19 tok/s on NVIDIA RTX 6000 Ada Generation |
| Gemma 3 — Gemma 3 27B Instruct | Q4_K_M · 16.30125 GB · ~40 tok/s on NVIDIA RTX 6000 Ada Generation |
购买此硬件 Apple MacBook Pro M5 Pro — 64 GB VRAM · 30 W board power立即云端部署 RunPod 上的 NVIDIA A40 — 低至 $0.44/小时 · 价格核实于 2026-08
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
FAQ
What LLMs run well with 48 GB VRAM?
Qwen 2.5 Family, Qwen 2.5 Family, Llama 3.3, Qwen 3, DeepSeek R1 all fit in 48 GB VRAM.
Which GPUs have 48 GB VRAM?
NVIDIA RTX 6000 Ada Generation, NVIDIA L40S, Apple M5 Pro, Apple M1 Max.
Can-I-Run Pages Near 48 GB
- DeepSeek R1 on NVIDIA RTX 6000 Ada Generation
- DeepSeek R1 on NVIDIA L40S
- Llama 3.3 on NVIDIA RTX 6000 Ada Generation
- Llama 3.3 on NVIDIA L40S
- Nemotron 70B on NVIDIA RTX 6000 Ada Generation
- Nemotron 70B on NVIDIA L40S
- Command R Family on NVIDIA RTX 6000 Ada Generation
- Command R Family on NVIDIA L40S