RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

RTX 3080 10GB vs RTX 4070 for local LLMs

Pick the RTX 4070 if you want to run bigger models (it runs 29 of the top 60 at 8-bit or better vs 21); pick the RTX 3080 10GB if the models you use already fit in it and you want more tokens per second.

Specs that matter for LLMs

RTX 3080 10GBRTX 4070
Memory (VRAM)10 GB12 GB
Usable for a model (our estimate)9.5 GB11.4 GB
Memory bandwidth760 GB/s504 GB/s
Launch MSRP$699$599
Launch $ per GB of memory$70$50
Top 60 models that fit (4-bit or better, 8K ctx)2929
…of those at 8-bit or better2129
Largest top-60 model that fitsQwen3.5 9BQwen3.5 9B
Offload headroom: more top-60 models via llama.cpp CPU offload (≥3 tok/s est., up to 128 GB RAM)16 more (6 more below 3 tok/s)14 more (6 more below 3 tok/s)

Top 60 = the 60 most-downloaded open models we track. Launch MSRP from vendor announcements. How we calculate.

Estimated speed on popular models

Best quant that fits at 8K context, with a tokens/sec ceiling from memory bandwidth (real speed is typically 50–80% of it). "Offload" means part of the model sits in system RAM. Estimates, not benchmarks.

ModelNeeds at 4-bitRTX 3080 10GBRTX 4070
Qwen3 8B6.5 GBQ6_K · ~113 tok/sQ8_0 · ~58 tok/s
Llama 3.1 8B Instruct6.2 GBQ6_K · ~115 tok/sQ8_0 · ~59 tok/s
Qwen3 14B10.3 GBOffload Q4_K_M, 32 GB RAM · ~14–24 tok/sQ3_K_M only (below 4-bit)
gpt-oss 20B11.8 GBOffload Q4_K_M, 32 GB RAM · ~49–85 tok/sOffload Q4_K_M, 32 GB RAM · ~75–104 tok/s
Gemma 3 27B IT17.3 GBOffload Q4_K_M, 32 GB RAM · ~2.6–5.2 tok/sOffload Q4_K_M, 32 GB RAM · ~3.1–6.0 tok/s
Qwen3 32B21.1 GBOffload Q4_K_M, 32 GB RAM · ~1.9–3.9 tok/sOffload Q4_K_M, 32 GB RAM · ~2.2–4.3 tok/s
Qwen3 Coder 30B A3B Instruct18.8 GBOffload Q4_K_M, 32 GB RAM · ~32–61 tok/sOffload Q4_K_M, 32 GB RAM · ~37–65 tok/s
Llama 3.3 70B Instruct42.7 GBOffload Q4_K_M, 64 GB RAM · ~0.7–1.4 tok/sOffload Q4_K_M, 64 GB RAM · ~0.7–1.4 tok/s
gpt-oss 120B59.6 GBOffload Q4_K_M, 64 GB RAM · ~13–26 tok/sOffload Q4_K_M, 64 GB RAM · ~13–26 tok/s

Models only one of them runs

None: of the top 60, both fit exactly the same models at 4-bit or better with 8K context.

More comparisons

RTX 4060 Ti 16GB vs RTX 4070RTX 4070 vs RTX 5070 All GPU comparisons

See every model on the RTX 3080 10GB or the RTX 4070, or try your own settings in the VRAM calculator.