Best LLMs for 24 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 24 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 Coder 32B | Q4_K_M · 19.32 GB · ~34 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Llama 3.3 — Llama 3.3 70B Instruct | Q2_K_XS (Tight) · 20.212500000000002 GB · ~33 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Qwen 3 — Qwen 3 32B | Q4_K_M · 19.802999999999997 GB · ~34 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| DeepSeek R1 — DeepSeek R1 Distill Qwen 32B | Q4_K_M · 19.32 GB · ~34 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Qwen 2.5 Family — Qwen 2.5 14B Instruct | Q4_K_M · 8.4525 GB · ~69 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Qwen 3 — Qwen 3 14B | Q4_K_M · 8.935500000000001 GB · ~67 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Codestral — Codestral 22B | Q4_K_M · 13.40325 GB · ~47 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Qwen 3.6 — Qwen 3.6 35B-A3B | Q4_K_M · 21.13125 GB · ~171 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| DeepSeek R1 — DeepSeek R1 Distill Qwen 14B | Q4_K_M · 8.4525 GB · ~70 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Phi-4 Family — Phi-4 (14B) | Q4_K_M · 8.4525 GB · ~69 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Gemma 4 — Gemma 4 31B | Q4_K_M · 18.71625 GB · ~36 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Gemma 3 — Gemma 3 27B Instruct | Q4_K_M · 16.30125 GB · ~34 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| GLM-4.7 / GLM-Z1 — GLM-Z1 32B (Reasoning) | Q4_K_M · 19.32 GB · ~35 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Qwen 3.5 — Qwen 3.5 35B-A3B | Q4_K_M · 21.13125 GB · ~171 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
| Mistral Small 3.1 — Mistral Small 3.1 24B | Q4_K_M · 14.248500000000002 GB · ~46 tok/s on NVIDIA GeForce RTX 5090 Laptop GPU |
购买此硬件 AMD Radeon RX 7900 XTX 24GB — 24 GB VRAM · 355 W board power立即云端部署 RunPod 上的 RTX 4090 — 低至 $0.34/小时 · 价格核实于 2026-07
或在 Vast.ai 比较，低至 $0.35/小时 (typical low · varies)
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 24 GB VRAM?
Qwen 2.5 Family, Llama 3.3, Qwen 3, DeepSeek R1, Qwen 2.5 Family all fit in 24 GB VRAM.
Which GPUs have 24 GB VRAM?
NVIDIA GeForce RTX 5090 Laptop GPU, AMD Radeon RX 7900 XTX, Apple M2, Apple M3.
Can-I-Run Pages Near 24 GB
- DeepSeek R1 on NVIDIA GeForce RTX 4090
- DeepSeek R1 on NVIDIA GeForce RTX 3090
- DeepSeek R1 on AMD Radeon RX 7900 XTX
- Llama 3.3 on NVIDIA GeForce RTX 4090
- Llama 3.3 on NVIDIA GeForce RTX 3090
- Llama 3.3 on AMD Radeon RX 7900 XTX
- Llama 3.3 on Apple M4 Pro
- Llama 3.3 on Apple M3