FreeLLMGPUs › NVIDIA
Best free AI models for the RTX 4070 / 4070 Super
RTX 4070 / 4070 Super: 12 GB of video memory, 504 GB/s. These are the free models it runs, ranked by Arena votes, with the speed you can expect.
Simulate your setup · Check the price on Amazon ↗ · Compare all GPUs
Bigger models with help from 64 GB of system RAM
Part of the model sits in system memory, which is much slower than video memory.
| Model | Arena score | Size | 4-bit file | Tokens/s |
|---|---|---|---|---|
| Gemma 4 31B |
1443 | 31.3 B | 20 GB | 6.4 |
| Qwen3.8-27B alibaba |
1441 | 27.8 B | 18 GB | 9.3 |
| Gemma 4 26B A4B google · MoE, 4 B active |
1434 | 25.8 B | 17 GB | 55 |
| Qwen3.5-27B alibaba |
1409 | 27.8 B | 18 GB | 9.3 |
| gemma-3-27b-it |
1358 | 27.4 B | 18 GB | 8.9 |
Popular small models
Official small models with no Arena votes yet, ordered by downloads on Hugging Face (popularity, not quality).
| Model | Downloads/month | Size | 4-bit file | Tokens/s |
|---|---|---|---|---|
| Qwen3-0.6B Qwen |
29.5M | 0.8 B | 1.7 GB | 216 |
| Qwen3-4B Qwen |
11.8M | 4 B | 3.6 GB | 98 |
| Qwen3-8B Qwen |
8.9M | 8.2 B | 6.2 GB | 60 |
| Qwen3-14B Qwen |
8.4M | 14.8 B | 10 GB | 37 |
| Qwen3.5-4B Qwen |
7.8M | 4.7 B | 4.0 GB | 112 |
| Qwen3.5-9B Qwen |
7.5M | 9.7 B | 7.1 GB | 60 |
Estimates at 4-bit (Q4_K_M) with an 8K context, calibrated on 44 real llama.cpp tests (typical error about ±10%). Tokens per second: about 10 is reading speed. As an Amazon Associate, FreeLLMArena earns from qualifying purchases; the links do not change the rankings.
Questions
What is the best free AI model for the RTX 4070 / 4070 Super?
No voted model fits entirely in 12 GB at 4-bit. Small models without Arena votes do, and larger ones run with help from system RAM, more slowly.
How big a model can the RTX 4070 / 4070 Super run?
About 16 billion parameters for a dense model at 4-bit with an 8K context, fully on the GPU. Mixture-of-experts models can be bigger, and with 64 GB of system RAM larger models still run, more slowly.
Is the RTX 4070 / 4070 Super good for local LLMs?
It has 12 GB of memory and 504 GB/s of bandwidth. Memory decides which models fit; bandwidth decides how fast they write. With less than 16 GB it runs small models well; bigger ones need system RAM and get slow.
Similar cards
- RTX 5070 12 GB · 672 GB/s
- Arc B580 12 GB · 456 GB/s
- RX 7700 XT 12 GB · 432 GB/s
- RTX 3060 12 GB 12 GB · 360 GB/s
- RTX 3080 10 GB 10 GB · 760 GB/s
- RTX 5080 16 GB · 960 GB/s