Entry-level RDNA 4 consumer GPU for learning AI and running smaller models.
By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.
What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.
Within a group, five factors set the order:
We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.
No providers match .
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.
One Radeon RX 9060 XT has 16 GB of VRAM. In practice, that's enough memory for roughly 15B parameters at 4-bit or 2B at 16-bit, assuming a 32K context. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
| Model | Memory (INT4 / FP4) | Radeon RX 9060 XTs needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
18 GB
|
2
|
–
|
–
|
Gemma 4 31B
30.7B
|
22 GB
|
2
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
67 GB
|
5
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
13
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
239 GB
|
17
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
22
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,544 GB
|
108
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP8 KV cache at 32K context per request (FP16/BF16 in the 16-bit column). GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.
AMD Radeon RX 9060 XT · Per GPU
| Compute · dense | |
|---|---|
| FP8 | 205 TFLOPS 410 with sparsity |
| FP16 / BF16 | 103 TFLOPS 205 with sparsity |
| INT8 | 205 TOPS 410 with sparsity |
| FP32 | 25.6 TFLOPS |
| Precision support | FP8FP16BF16FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 16 GB GDDR6 |
| Bandwidth | 320 GB/s |
| Bus width | 128-bit |
| Silicon | |
|---|---|
| Architecture | RDNA 4 |
| Process | 4nm |
| Transistors | 29.7 billion |
| Shader cores | 2,048 Stream processors |
| Matrix cores | 64 |
| Compute units | 32 |
| Fabric and host | |
|---|---|
| Host interface | PCIe 5.0 x16 |
| Power | |
|---|---|
| Board power | 160 W |
The cheapest verified in-stock estimate is $94 per month on-demand, $36 spot.
GetDeploying currently tracks Radeon RX 9060 XT configs from 1 provider. Salad has verified in-stock on-demand configs. See the full price comparison above for every provider and config.
One Radeon RX 9060 XT runs models up to roughly 15B parameters at 4-bit quantization or 2B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
16GB on a 160W RDNA 4 card with FP8 matrix support. Enough for a 7B model at 8-bit with room for context, or a 13B model at 4-bit, as a low-power entry point for ROCm development.
320 GB/s of memory bandwidth, half that of the RX 9070 XT, limits token generation speed, and the 8GB version fits only small or heavily quantized models. Where a framework needs CUDA, the RTX 5060 Ti is the 16GB consumer counterpart. The ROCm software ecosystem, while rapidly improving, is narrower than CUDA.
Nvidia RTX 5060 Ti
16 GB GDDR7 · 60% more bandwidth than the Radeon RX 9060 XT
AMD Radeon RX 7800 XT
16 GB GDDR6 · 95% more bandwidth than the Radeon RX 9060 XT
AMD Radeon RX 9070 XT
16 GB GDDR6 · 2x the bandwidth of the Radeon RX 9060 XT
Last updated
