Best local AI models for NVIDIA Quadro RTX 3000 MAX-Q
6 GB GDDR6. At a 4k context, 114 of the 233 models in our catalog with verified parameter counts fit fully, up to Granite 3.3 2B / 8B at 8B parameters.
Check your own machine against every model →The largest models that fit fully
The 30 largest of the 114 models that fit; every smaller model in the catalog fits too. Best quant means the highest quality compression whose weights and 4k context both sit inside the memory.
| Model | Parameters | Best quant that fits | Memory used at 4k |
|---|---|---|---|
| Granite 3.3 2B / 8B | 8B | Q4_K_M | 5.9 GB |
| Ministral 3B / 8B | 8B | Q4_K_M | 5.9 GB |
| InternLM 3 8B | 8B | Q4_K_M | 5.9 GB |
| OpenCoder 1.5B / 8B | 8B | Q4_K_M | 5.9 GB |
| Seed-Coder 8B | 8B | Q4_K_M | 5.9 GB |
| MiniCPM-V 2.6 / MiniCPM-o 2.6 | 8B | Q4_K_M | 5.9 GB |
| Idefics 3 8B | 8B | Q4_K_M | 5.9 GB |
| Fuyu-8B | 8B | Q4_K_M | 5.9 GB |
| Emu3 | 8B | Q4_K_M | 5.9 GB |
| Stable Diffusion 3.5 Large / Turbo | 8B | Q4_K_M | 5.9 GB |
| EXAONE 3.5 2.4B / 7.8B | 7.8B | Q4_K_M | 5.7 GB |
| Mistral 7B | 7B | Q4_K_M | 5.7 GB |
| Qwen2.5 0.5B / 1.5B / 3B / 7B | 7B | Q5_K_M | 6 GB |
| OLMo 2 1B / 7B | 7B | Q5_K_M | 6 GB |
| Falcon 3 1B / 3B / 7B | 7B | Q5_K_M | 6 GB |
| Command R7B | 7B | Q5_K_M | 6 GB |
| OpenHermes 2.5 | 7B | Q5_K_M | 6 GB |
| Zephyr 7B Beta | 7B | Q5_K_M | 6 GB |
| OpenChat 3.5 | 7B | Q5_K_M | 6 GB |
| Starling LM 7B | 7B | Q5_K_M | 6 GB |
| Codestral Mamba 7B | 7B | Q5_K_M | 6 GB |
| CodeGemma 2B / 7B | 7B | Q5_K_M | 6 GB |
| aiXcoder-7B | 7B | Q5_K_M | 6 GB |
| Nxcode / CodeQwen 1.5 7B | 7B | Q5_K_M | 6 GB |
| Janus-Pro 1B / 7B | 7B | Q5_K_M | 6 GB |
| Ruyi-Mini-7B | 7B | Q5_K_M | 6 GB |
| Qwen2-Audio 7B | 7B | Q5_K_M | 6 GB |
| Qwen2.5-Omni 3B / 7B | 7B | Q5_K_M | 6 GB |
| YuE | 7B | Q5_K_M | 6 GB |
| Magicoder-S-DS 6.7B | 6.7B | Q5_K_M | 5.7 GB |
Close, but only with CPU offload
These need more than the card holds at their smallest practical quant, so part of the model runs from system memory (figures assume 32 GB of it). They work, several times slower.
| Model | Parameters | Memory at Q4_K_M | System RAM at 4k |
|---|---|---|---|
| Llama 3.1 8B | 8B | 6.4 GB needed | 8.4 GB |
| Chroma | 8.9B | 6.5 GB needed | 8.5 GB |
| Gemma 2 9B | 9B | 8 GB needed | 10 GB |
| Nemotron Nano 4B / 9B | 9B | 6.6 GB needed | 8.6 GB |
| GLM-4 9B / GLM-4.5-Air | 9B | 6.6 GB needed | 8.6 GB |
| Yi-Coder 1.5B / 9B | 9B | 6.6 GB needed | 8.6 GB |
| GLM-4-9B-Chat / CodeGeeX4 | 9B | 6.6 GB needed | 8.6 GB |
| GLM-4V-9B / GLM-4.1V-Thinking | 9B | 6.6 GB needed | 8.6 GB |
| Mochi 1 | 10B | 7.3 GB needed | 9.3 GB |
| Open-Sora 2.0 | 11B | 8.1 GB needed | 10.1 GB |
How to read this
The NVIDIA Quadro RTX 3000 MAX-Q is a mobile workstation graphics card equipped with 6 GB of GDDR6 memory. This dedicated memory size determines the maximum size of the artificial intelligence models you can run entirely on the graphics hardware. Keeping a model fully inside the video memory ensures the fastest possible processing speeds for your tasks.
To fit larger models into the 6 GB limit you must use quantized versions. The quant column indicates the compression level applied to the weights of the model. For example a Q4_K_M quantization represents a four bit format that reduces the model footprint while preserving most of its original intelligence. A Q5_K_M quantization uses a five bit format which offers slightly higher accuracy but requires more memory.
For models that fit entirely within your video memory you can run 8B models like Granite 3.3 8B, Ministral 8B, InternLM 3 8B, OpenCoder 8B, Seed-Coder 8B, MiniCPM-V 2.6, Idefics 3 8B, Fuyu-8B, Emu3, or Stable Diffusion 3.5 Large at Q4_K_M quantizations using 5.9 GB. You can also run EXAONE 3.5 7.8B at Q4_K_M using 5.7 GB. Mistral 7B at Q4_K_M uses 5.7 GB. Magicoder-S-DS 6.7B at Q5_K_M uses 5.7 GB.
Other 7B models can run at Q5_K_M quantizations using exactly 6 GB of video memory. This group includes Qwen2.5 7B, OLMo 2 7B, Falcon 3 7B, Command R7B, OpenHermes 2.5, Zephyr 7B Beta, OpenChat 3.5, Starling LM 7B, Codestral Mamba 7B, CodeGemma 7B, aiXcoder-7B, Nxcode, Janus-Pro 7B, Ruyi-Mini-7B, Qwen2-Audio 7B, Qwen2.5-Omni 7B, and YuE.
When a model exceeds 6 GB you must offload some layers to your system RAM. Assuming you have 32 GB of system RAM you can run Llama 3.1 8B at Q4_K_M which needs 6.4 GB of video memory and 8.4 GB of system RAM. Gemma 2 9B at Q4_K_M needs 8 GB of video memory and 10 GB of system RAM. Mochi 1 needs 7.3 GB of video memory and 9.3 GB of system RAM. Open-Sora 2.0 needs 8.1 GB of video memory and 10.1 GB of system RAM.
Other offload options include Chroma 8.9B which needs 6.5 GB of video memory and 8.5 GB of system RAM. Nemotron Nano 9B, GLM-4 9B, Yi-Coder 9B, GLM-4-9B-Chat, and GLM-4V-9B all need 6.6 GB of video memory and 8.6 GB of system RAM at Q4_K_M. Offloading layers to system RAM allows you to run these larger models but it reduces your processing speed because system RAM is much slower than GDDR6 memory.
You must also consider the context window size when planning your memory usage. The memory figures listed are calculated using a standard 4k context window. If you increase the context length to process longer documents or conversations the memory requirements will grow. This extra demand might force you to use a lower quantization level or offload more layers to your system RAM.