BaichuanMed OCR 72B i1 needs ~56.8 GB but RTX 5090 32GB only has 32.0 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
24.8 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
6.5 tok/s
TTFT
29810 ms
Safe context
4K
Memory
56.8 GB / 32.0 GB
Offload
40%
Usable VRAM is the main blocker for this model.
Not enough usable memory
The model needs 56.8 GB, but this setup only exposes 32.0 GB of usable VRAM.
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 | 7.6 tok/s | 13890 ms | 4K |
| Coding | F | Too heavy | 6.5 tok/s | 29810 ms | 4K |
| Agentic Coding | F | Too heavy | 4.9 tok/s | 57528 ms | 4K |
| Reasoning | F | Too heavy | 6.5 tok/s | 35230 ms | 4K |
| RAG | F | Too heavy | 4.9 tok/s | 71910 ms | 4K |
How BaichuanMed OCR 72B i1 (72B params) fits at each quantization level on RTX 5090 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 28.1 GB | Low | F0 |
Q3_K_S | 3 | 35.3 GB | Low | F0 |
NVFP4 | 4 |
Upgrade options
NVIDIA A16 64GBBudget pickMakes 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.
~$6,500 MSRP
RTX PRO 6000 Blackwell Workstation Edition 96GBBest valueMakes 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.
~$9,999 MSRP
NVIDIA DGX Spark 128GBNVIDIA upgradeMakes 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.
No, BaichuanMed OCR 72B i1 requires more memory than RTX 5090 32GB provides.
BaichuanMed OCR 72B i1 (72B parameters) requires approximately 56.8 GB of memory with Q4_K_M quantization.
The recommended quantization for BaichuanMed OCR 72B i1 is Q4_K_M, which balances quality and memory efficiency.
On RTX 5090 32GB, BaichuanMed OCR 72B i1 achieves approximately 6.5 tokens per second decode speed with a time-to-first-token of 29810ms using Q4_K_M quantization.
For coding workloads, BaichuanMed OCR 72B i1 on RTX 5090 32GB receives a F grade with 6.5 tok/s and 4K context.
On RTX 5090 32GB, BaichuanMed OCR 72B i1 can safely use up to 4K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-mradermacher--baichuanmed-ocr-72b-i1-gguf-on-rtx-5090-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| Medium |
| F0 |
Q4_K_M | 4 | 43.9 GB | Medium | F0 |
Q5_K_M | 5 | 51.8 GB | High | F0 |
Q6_K | 6 | 59.0 GB | High | F0 |
Q8_0 | 8 | 77.0 GB | Very High | F0 |
F16 | 16 | 147.6 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.
