RDNA 3 flagship consumer GPU for local AI inference with 24GB of memory.
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 7900 XTX has 24 GB of VRAM. In practice, that's enough memory for roughly 21B parameters at 4-bit or 6B 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 7900 XTXs needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
1
|
–
|
–
|
Gemma 4 31B
30.7B
|
24 GB
|
2
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
4
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
9
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
12
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
15
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
72
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP16/BF16 KV cache at 32K context per request. 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 7900 XTX · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 123 TFLOPS |
| INT8 | 123 TOPS |
| FP32 | 61.4 TFLOPS |
| Precision support | FP16BF16FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 24 GB GDDR6 |
| Bandwidth | 960 GB/s |
| Bus width | 384-bit |
| Silicon | |
|---|---|
| Architecture | RDNA 3 |
| Process | 5nm / 6nm |
| Transistors | 58 billion |
| Shader cores | 6,144 Stream processors |
| Matrix cores | 192 |
| Compute units | 96 |
| Power | |
|---|---|
| Board power | 355 W |
The cheapest verified in-stock estimate is $122 per month on-demand, $50 spot.
GetDeploying currently tracks Radeon RX 7900 XTX 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 7900 XTX runs models up to roughly 21B parameters at 4-bit quantization or 6B 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.
24GB at 960 GB/s on one consumer card. Holds a 7B to 8B model at FP16 with room for context, or a 30B-class model at 4-bit, and AMD lists it as supported by ROCm on Linux.
RDNA 3 has no FP8 and no structured sparsity, and its 123 TFLOPS dense FP16 trails the RTX 4090 on the same 24GB. For models that fit in 16GB, the RX 9070 XT adds FP8 and a higher dense FP16 rate. The ROCm software ecosystem, while rapidly improving, is narrower than CUDA.
AMD Radeon RX 7900 XT
20 GB GDDR6 · 17% less bandwidth than the Radeon RX 7900 XTX
AMD Radeon RX 9070 XT
16 GB GDDR6 · 33% less bandwidth than the Radeon RX 7900 XTX
Last updated
