Radeon RX 9060 XT 8G — what LLMs can it run?
36 of 87 indexed models fit comfortably in 8GB at 4K context, each at the highest-quality quant that still leaves headroom.
The short answer for Radeon RX 9060 XT 8G
8 GB, 320 GB/s GDDR6. 36 of 87 models in this index fit comfortably at 4K context; 43 load at all.
- Biggest that fits
- Stable LM 2 12B Chat — 7.0 GB at AWQ INT4 — 1.0 GB spare at 4K, so longer context comes out of a thin margin.
- Room to grow
- Qwen3 4B Instruct — 4.0 GB at Q6_K — under 60% of the card, which leaves 4.0 GB for a long context window or a second process.
- Speed ceiling
- Llama 3.1 8B Instruct at Q4_K_M reads 4.6 GB of weights per token, so 320 GB/s puts a hard ceiling near 69 tok/s. That is arithmetic on two published numbers, not a benchmark — real throughput lands below it. No run on this card has been measured here, so there is nothing to compare the ceiling against.
- The wall you will hit
- Backend coverage, not capacity. At 320 GB/s the memory system is competitive with NVIDIA cards of the same size; what varies is whether your runtime has a working ROCm build for your kernel and card. llama.cpp and vLLM both ship official ROCm support — this is a setup question, not a hardware ceiling.
14B · 4
| Model | Quant | Est. VRAM | Headroom | tok/s on RTX 4090 |
|---|---|---|---|---|
| Stable LM 2 12B Chat12B | AWQ INT4 | 7.01 GB | +1 GB | 142Estimated |
| Solar 10.7B Instruct11B | AWQ INT4 | 6.42 GB | +1.6 GB | 168Estimated |
| Falcon 3 10B Instruct10B | GPTQ INT4 | 6.12 GB | +1.9 GB | 155Estimated |
| Gemma 2 9B Instruct9B | AWQ INT4 | 6.27 GB | +1.7 GB | 188Estimated |
7B · 22
| Model | Quant | Est. VRAM | Headroom | tok/s on RTX 4090 |
|---|---|---|---|---|
| GLM-4-9B-Chat9B | Q4_K_M | 5.87 GB | +2.1 GB | 135Estimated |
| Qwen3-VL 8B Instruct8B | Q4_K_M | 6.19 GB | +1.8 GB | 140Community |
| Ministral 3 8B Instruct8B | Q5_K_M | 6.92 GB | +1.1 GB | — |
| Qwen2-VL 7B Instruct7B | Q4_K_M | 5.49 GB | +2.5 GB | 72Estimated |
| Granite 3.1 8B Instruct8B | Q4_K_M | 5.88 GB | +2.1 GB | 142Estimated |
| Qwen3 8B Instruct8B | Q4_K_M | 5.81 GB | +2.2 GB | 142 |
| Llama 3.1 8B Instruct8B | Q4_K_M | 5.64 GB | +2.4 GB | 148 |
| Nous Hermes 3 Llama 3.1 8B8B | Q4_K_M | 5.64 GB | +2.4 GB | 148Estimated |
| Aya 23 8B8B | Q4_K_M | 5.64 GB | +2.4 GB | 145Estimated |
| OpenChat 3.6 8B8B | Q4_K_M | 5.64 GB | +2.4 GB | 146Estimated |
| DeepSeek-R1-Distill-Llama-8B8B | Q5_K_M | 6.51 GB | +1.5 GB | 128Estimated |
| InternLM2 7B Chat7B | Q4_K_M | 5.45 GB | +2.6 GB | 148Estimated |
| Qwen2.5 7B Instruct7B | Q6_K | 6.77 GB | +1.2 GB | 132 |
| Qwen2.5-Coder 7B Instruct7B | Q4_K_M | 5.07 GB | +2.9 GB | 158Estimated |
| DeepSeek-R1-Distill-Qwen-7B7B | Q4_K_M | 5.07 GB | +2.9 GB | 152Estimated |
| Gemma 4 E4B ITE4B | Q4_K_M | 4.88 GB | +3.1 GB | — |
| OLMo 2 7B Instruct7B | Q4_K_M | 6.82 GB | +1.2 GB | 150Estimated |
| WizardLM-2 7B7B | Q4_K_M | 5.14 GB | +2.9 GB | 152Estimated |
| Mistral 7B Instruct v0.37B | Q6_K | 6.75 GB | +1.3 GB | 135Estimated |
| Zephyr 7B Beta7B | Q6_K | 6.75 GB | +1.3 GB | 132Estimated |
| Gemma 4 E2B ITE2B | Q8_0 | 5.2 GB | +2.8 GB | — |
| Gemma 3 4B IT4B | Q8_0 | 5.05 GB | +3 GB | 145Estimated |
≤3B · 10
| Model | Quant | Est. VRAM | Headroom | tok/s on RTX 4090 |
|---|---|---|---|---|
| Qwen3 4B Instruct4B | Q6_K | 4.05 GB | +4 GB | 145 |
| Phi-4 Mini Instruct3.8B | Q8_0 | 4.81 GB | +3.2 GB | 262Estimated |
| Phi-3.5 Mini Instruct3.8B | Q8_0 | 5.89 GB | +2.1 GB | 255Estimated |
| Llama 3.2 3B Instruct3B | Q8_0 | 4.05 GB | +4 GB | 285Estimated |
| Qwen2.5 3B Instruct3B | Q8_0 | 3.59 GB | +4.4 GB | 290Estimated |
| Gemma 2 2B Instruct2B | Q8_0 | 3.34 GB | +4.7 GB | 320Estimated |
| Qwen3 1.7B Instruct1.7B | Q8_0 | 2.39 GB | +5.6 GB | 240Estimated |
| Qwen2.5 1.5B Instruct1.5B | Q8_0 | 1.83 GB | +6.2 GB | 410Estimated |
| Llama 3.2 1B Instruct1B | Q8_0 | 1.51 GB | +6.5 GB | 450Estimated |
| Qwen2.5 0.5B Instruct0.5B | Q8_0 | 0.6 GB | +7.4 GB | 540Estimated |
How this list is built
Each row is the lowest-perplexity-loss quant of that model whose estimated total — weights plus KV cache at 4K context plus activation buffer — uses at most 88% of the card. That is the calculator's "green" threshold, so every row here has real headroom rather than only just fitting. Raise the context length and the list shortens; the calculator lets you check any combination directly.
A further 7 models load but with no headroom to spare (up to 105% of VRAM) — the Quant Hub’s GPU chips count those too, which is why its number is higher.
Measured on this card
No benchmark runs in this index were recorded on a Radeon RX 9060 XT 8G. Every figure on this page is calculated from the model architecture and the quant level — treat them as estimates, not measurements. The speed column in the tables above is an RTX 4090 figure shown for reference — it is not a speed on this card.
Stepping up
A Radeon RX 7700 XT (12GB) fits 11 more of the indexed models than this card. Radeon RX 7700 XT →
Common questions
What is the best local LLM for a Radeon RX 9060 XT 8G?
For everyday use, Qwen3 4B Instruct at Q6_K — about 4.0 GB of the card's 8 GB at 4K context, leaving 4.0 GB for a longer window. If you want the largest thing that will load, that is Stable LM 2 12B Chat at AWQ INT4 (7.0 GB, 1.0 GB spare). "Best" here means best fit for the memory budget — this index does not run task benchmarks, so it cannot tell you which model is smarter.
Can a Radeon RX 9060 XT 8G run Mistral Nemo 12B Instruct?
Only just. Its smallest build here, AWQ INT4, needs about 7.1 GB against 8.0 GB usable — that loads with nothing else running, with no margin for a longer context window. It is not on the list above, which requires a model to stay inside 88% of usable capacity.
How many tokens per second does a Radeon RX 9060 XT 8G do on an 8B model at Q4?
This index has no measured run on this card, so it does not publish a figure. What can be stated from specifications: generating a token requires reading every weight once, Llama 3.1 8B Instruct at Q4_K_M is 4.6 GB of weights, and this card moves 320 GB/s — a ceiling near 69 tok/s. Batch size, context length, the runtime and how much of the model sits in cache all take you below it.
Radeon RX 9060 XT 8G or RTX 3070 Ti for local LLMs?
They hold the same models: 8 GB against 8 GB fits 36 and 36 of 87 respectively at 4K. The difference is throughput — 320 GB/s against 608 GB/s, a 1.9× gap in how fast the weights can be read, which is what token generation is bound by. The RTX 3070 Ti generates faster on any model both can hold.
36 of 87 indexed models fit comfortably in 8GB at 4K context, each at the highest-quality quant that still leaves headroom.
This page's figures change when the model or the runtime does.Last updated 2026-10-02 RSS → /feed.xml