← CanIRunLocal · All hardware · All models
No. DeepSeek R1 Distill Llama 70B does not fit on RTX 3090 24GB: Q4_K_M needs 47.1 GB and 23.5 GB is usable.
Hardware: RTX 3090 24GB · Model: DeepSeek R1 Distill Llama 70B
RTX 3090 24GB has 24 GB of VRAM and 936 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 23.5 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 | 23.5 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 3090 24GB run DeepSeek R1 Distill Qwen 32B?
Open RTX 3090 24GB 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