← CanIRunLocal · All hardware · All models
No. DeepSeek R1 Distill Qwen 32B does not fit on RTX 5070 12GB: Q4_K_M needs 22.2 GB and 11.5 GB is usable.
Hardware: RTX 5070 12GB · Model: DeepSeek R1 Distill Qwen 32B
RTX 5070 12GB has 12 GB of VRAM and 672 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 11.5 GB. Partial offload may also use 60% of that system RAM. DeepSeek R1 Distill Qwen 32B (32.8B, DeepSeek) at Q4_K_M is a 20 GB download and needs 22.2 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 20 GB |
| Memory needed | 22.2 GB |
| Usable fast memory | 11.5 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run deepseek-r1:32b |
Smallest hardware that runs it: RTX 4060 Ti 16GB at Q4_K_M (partial offload (slower), 22.2 GB needed, 15.5 GB usable, about 4 tok/s (estimate)). Can a RTX 4060 Ti 16GB run DeepSeek R1 Distill Qwen 32B?
A smaller DeepSeek model that fits this hardware: DeepSeek Coder V2 Lite 16B (MoE) at Q4_K_M (fits in fast memory, 11 GB). Can a RTX 5070 12GB run DeepSeek Coder V2 Lite 16B (MoE)?
Open RTX 5070 12GB 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