What AI models run on the RX 7800 XT?
The RX 7800 XT has 16 GB of VRAM (624 GB/s). About 15.2 GB is usable for a model. 200 of 298 open models we track fit at 8K context.
This card has 16 GB of VRAM. See every model that fits in 16 GB VRAM. Other 16 GB hardware: RTX 4060 Ti 16GB, RTX 4070 Ti Super, RTX 4080, RTX 4080 Super, RTX 5060 Ti 16GB, RTX 5070 Ti, RTX 5080, RX 7900 GRE.
Compare for local LLMs: RX 7800 XT vs RTX 4060 Ti 16GB all comparisons
Using a specific tool? Ollama models that run on the RX 7800 XT · LM Studio · llama.cpp offload
Models that fit, largest first
Bigger models with CPU offload
These popular models don't fit in the RX 7800 XT's VRAM at 4-bit, but run with llama.cpp offload, keeping part of the model in system RAM. Speed range is DDR4-3200 to DDR5-6000 (estimate). Method.
| Model | Params | Offload plan |
|---|---|---|
| GLM 5.3 Flash | 321B MoE | Offload Q2_K, 128 GB RAM · ~7.3–14 tok/s |
| gpt-oss 120B | 117B MoE | Offload Q4_K_M, 64 GB RAM · ~14–28 tok/s |
| DeepSeek V4 Flash 0731 | 304B MoE | Offload Q2_K, 128 GB RAM · ~8.0–14 tok/s |
| DeepSeek V4 Flash | 291B MoE | Offload Q3_K_M, 128 GB RAM · ~7.1–14 tok/s |
| GLM 4.5 Air | 110B MoE | Offload Q4_K_M, 64 GB RAM · ~5.6–11 tok/s |
| MiniMax M2.5 | 229B MoE | Offload Q4_K_M, 128 GB RAM · ~5.6–11 tok/s |
| Hy3 | 299B MoE | Offload Q3_K_M, 128 GB RAM · ~4.2–8.3 tok/s |
Comparing cards? The RX 7800 XT (launch MSRP $499) is in best GPUs for local LLMs under $500. See also Mac vs PC.
Just too big at 4-bit
These need up to 35% more memory than the RX 7800 XT has at Q4_K_M and 8K context. A smaller quant or shorter context may work.
| Model | Q4_K_M needs | Short by |
|---|---|---|
| Trinity Mini | 15.8 GB | 0.6 GB |
| GLiDE 27B | 16.2 GB | 1.0 GB |
| MiniMax H3 Image PE | 16.8 GB | 1.6 GB |
| DiffusionGemma 26B A4B IT | 17.1 GB | 1.9 GB |
| Gemma 4 26B A4B IT | 17.3 GB | 2.1 GB |
| Gemma 3 27B IT | 17.3 GB | 2.1 GB |
| Arete 27B | 17.4 GB | 2.2 GB |
| Qwen3.8 27B | 17.6 GB | 2.4 GB |
| Muse Glimmer 30B | 17.9 GB | 2.7 GB |
| Qwen3.5 27B | 18.1 GB | 2.9 GB |
| Qwen3.6 27B | 18.1 GB | 2.9 GB |
| GLM 4.7 Flash | 18.3 GB | 3.1 GB |
| Hy Memory 30B A3B | 18.5 GB | 3.3 GB |
| Qwen3 Coder 30B A3B Instruct | 18.8 GB | 3.6 GB |
| North Mini Code 1.0 | 18.8 GB | 3.6 GB |
Questions
What is the biggest model that runs on the RX 7800 XT?
Of the models we track, the largest that fits at 8K context is Maxwell V1 Flash (37B) at Q2_K, needing about 14.0 GB.
How much of the RX 7800 XT's memory can a model use?
About 15.2 GB: we assume 95% of the 16 GB is usable after driver and display overhead.
Spec source: AMD specifications. Model data: Hugging Face Hub API. Speed is a bandwidth ceiling (bandwidth ÷ bytes read per token), not a benchmark. Methodology · Report an error.