 |
VOOZH | about |
MPT-30B-Instruct needs ~48.6 GB but Quadro RTX 6000 24GB only has 24.0 GB. Try a smaller quantization or lighter model.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
24.6 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
3.4 tok/s
TTFT
57176 ms
Safe context
4K
Memory
48.6 GB / 24.0 GB
Offload
50%
Usable VRAM is the main blocker for this model.
Not enough usable memory
The model needs 48.6 GB, but this setup only exposes 24.0 GB of usable VRAM.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Add more VRAM headroom
The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 6.2 tok/s | 17024 ms | 4K |
| Coding | F | Too heavy | 3.4 tok/s | 57176 ms | 4K |
| Agentic Coding | F | Too heavy | 3.3 tok/s | 85739 ms | 4K |
| Reasoning | F | Too heavy | 3.4 tok/s | 67571 ms | 4K |
| RAG | F | Too heavy | 3.3 tok/s | 107173 ms | 4K |
How MPT-30B-Instruct (30B params) fits at each quantization level on Quadro RTX 6000 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 11.7 GB | Low | A71 |
Q3_K_S | 3 | 14.7 GB | Low | A70 |
NVFP4 | 4 |
Upgrade options
Makes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 435%.
~$4,650 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 959%.
~$4,999 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 518%.
~$5,500 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$40,000 MSRP
16.8 GB |
| Medium |
| A70 |
Q4_K_MBest for your GPU | 4 | 18.3 GB | Medium | B70 |
Q5_K_M | 5 | 21.6 GB | High | F0 |
Q6_K | 6 | 24.6 GB | High | F0 |
Q8_0 | 8 | 32.1 GB | Very High | F0 |
F16 | 16 | 61.5 GB | Maximum | F0 |
Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.
