FreeLLMGPUs › AMD
Best free AI models for the RX 7900 XT
RX 7900 XT: 20 GB of video memory, 800 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
Voted models that fit fully on the GPU
| Model | Arena score | Size | 4-bit file | Tokens/s |
|---|---|---|---|---|
| Qwen3.8-27B alibaba |
1441 | 27.8 B | 18 GB | 35 |
| Gemma 4 26B A4B google · MoE, 4 B active |
1434 | 25.8 B | 17 GB | 132 |
| Qwen3.5-27B alibaba |
1409 | 27.8 B | 18 GB | 35 |
| gemma-3-27b-it |
1358 | 27.4 B | 18 GB | 34 |
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 | 18 |
| glm-4.6v zai · MoE, 14.3 B active |
1376 | 107.7 B | 66 GB | 11 |
| glm-4.5v zai · MoE, 14.3 B active |
1333 | 107.7 B | 66 GB | 11 |
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 | 305 |
| Qwen3-4B Qwen |
11.8M | 4 B | 3.6 GB | 147 |
| Qwen3-8B Qwen |
8.9M | 8.2 B | 6.2 GB | 92 |
| Qwen3-14B Qwen |
8.4M | 14.8 B | 10 GB | 57 |
| Qwen3.5-4B Qwen |
7.8M | 4.7 B | 4.0 GB | 167 |
| Qwen3.5-9B Qwen |
7.5M | 9.7 B | 7.1 GB | 92 |
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 7900 XT?
Qwen3.8-27B (Arena score 1441) is the highest-voted open model that fits entirely in 20 GB of video memory at 4-bit, writing about 35 tokens per second.
How big a model can the RX 7900 XT run?
About 29 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 7900 XT good for local LLMs?
It has 20 GB of memory and 800 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 3090 Ti 24 GB · 1008 GB/s
- RTX 4090 24 GB · 1008 GB/s
- RTX 5080 16 GB · 960 GB/s
- RX 7900 XTX 24 GB · 960 GB/s
- RTX 3090 24 GB · 936 GB/s
- RTX 5070 Ti 16 GB · 896 GB/s