← CanIRunLocal · All hardware · All models
No. DeepSeek R1 Distill Llama 70B does not fit on RTX 5090 32GB: Q4_K_M needs 47.1 GB and 31.5 GB is usable.
Hardware: RTX 5090 32GB · Model: DeepSeek R1 Distill Llama 70B
RTX 5090 32GB has 32 GB of VRAM and 1792 GB/s of memory bandwidth. The checker holds back 0.5 GB of VRAM for the driver and assumes 16 GB of system RAM, so fast memory usable by Ollama is 31.5 GB. Partial offload may also use 60% of that system RAM. DeepSeek R1 Distill Llama 70B (70.6B, DeepSeek) at Q4_K_M is a 43 GB download and needs 47.1 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 43 GB |
| Memory needed | 47.1 GB |
| Usable fast memory | 31.5 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run deepseek-r1:70b |
Smallest hardware that runs it: M1 Max (32c GPU) 64GB at Q4_K_M (fits in fast memory, 47.1 GB needed, 48.0 GB usable, about 7 tok/s (estimate)). Can a M1 Max (32c GPU) 64GB run DeepSeek R1 Distill Llama 70B?
A smaller DeepSeek model that fits this hardware: DeepSeek R1 Distill Qwen 32B at Q4_K_M (fits in fast memory, 22.2 GB). Can a RTX 5090 32GB run DeepSeek R1 Distill Qwen 32B?
Open RTX 5090 32GB in the checkerEstimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt