FreeLLMGPUs › AMD
Best free AI models for the RX 9070 / 9070 XT
RX 9070 / 9070 XT: 16 GB of video memory, 640 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 | 9.4 |
| Qwen3.8-27B alibaba |
1441 | 27.8 B | 18 GB | 17 |
| Gemma 4 26B A4B google · MoE, 4 B active |
1434 | 25.8 B | 17 GB | 99 |
| Qwen3.5-27B alibaba |
1409 | 27.8 B | 18 GB | 17 |
| gemma-3-27b-it |
1358 | 27.4 B | 18 GB | 16 |
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 | 260 |
| Qwen3-4B Qwen |
11.8M | 4 B | 3.6 GB | 121 |
| Qwen3-8B Qwen |
8.9M | 8.2 B | 6.2 GB | 75 |
| Qwen3-14B Qwen |
8.4M | 14.8 B | 10 GB | 46 |
| Qwen3.5-4B Qwen |
7.8M | 4.7 B | 4.0 GB | 138 |
| Qwen3.5-9B Qwen |
7.5M | 9.7 B | 7.1 GB | 75 |
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 RX 9070 / 9070 XT?
No voted model fits entirely in 16 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 RX 9070 / 9070 XT run?
About 23 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 RX 9070 / 9070 XT good for local LLMs?
It has 16 GB of memory and 640 GB/s of bandwidth. Memory decides which models fit; bandwidth decides how fast they write. With 16 GB it runs models up to about 20 B fully on the GPU; 27–32 B models need help from system RAM.
Similar cards
- RTX 5080 16 GB · 960 GB/s
- RTX 5070 Ti 16 GB · 896 GB/s
- RTX 4080 Super 16 GB · 736 GB/s
- RTX 4070 Ti Super 16 GB · 672 GB/s
- RX 7800 XT 16 GB · 624 GB/s
- RTX 5060 Ti 16 GB 16 GB · 448 GB/s