WHAT THIS CARD IS WORTH
RX 7900 XTX holds 293 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is DeepSeek Coder 33B at IQ4_XS.
TOKENS/SEC PER $100
10.2
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
2.40 GB
what memory costs on this card
THE BIGGEST IT TAKES
AGAINST CARDS OF SIMILAR MEMORY
RX 7900 XTX24 GB$99910.2 tok/s per $100
Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.
▸ DEVICE UNDER TEST
AMD RX 7900 XTX — 24 GB VRAM.
▸ RX 7900 XTX SPEC
- BRAND
- AMD
- VRAM
- 24 GB GDDR6
- BANDWIDTH
- 960 GB/s
- FP16 COMPUTE
- 123 TFLOPS
- FP32 COMPUTE
- 61 TFLOPS
- STREAM PROCESSORS
- 6,144
- TDP
- 355 W
- ARCHITECTURE
- RDNA3
- MSRP
- $999
▸ AI CAPABILITY
293/ 449 models @ Q4
With 24 GB VRAM and 960 GB/s bandwidth, this GPU handles models up to 30.5B parameters.
Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~110 tok/s.
RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR RX 7900 XTX
293 FIT · SHOWING 20| MODEL | SIZE | VRAM Q4 | TOK/S | AVG |
|---|---|---|---|---|
| Qwen3 30B A3B | 30.5B | 19.1 GB | 284 | 46.7 |
| Qwen3-Coder 30B-A3B | 30.5B | 19.1 GB | 259 | 36.9 |
| Qwen3-30B-A3B Instruct 2507 | 30.5B | 19.1 GB | 259 | 43.0 |
| MPT-30B | 30B | 18.8 GB | 28 | 26.8 |
| OPT 30B | 30B | 18.8 GB | 28 | 6.3 |
| Qwen3-Omni 30B-A3B | 30B | 18.8 GB | 284 | 40.6 |
| Granite 4.1 30B | 30B | 18.8 GB | 28 | 24.7 |
| TranslateGemma 27B | 28.84B | 18.1 GB | 30 | 38.6 |
| PaliGemma 2 28B | 28B | 17.6 GB | 30 | 38.6 |
| ERNIE 4.5 VL 28B A3B Thinking | 28B | 17.6 GB | 284 | — |
| Qwen3.5-27B | 27.8B | 17.5 GB | 31 | 59.4 |
| Qwen 3.8 27B | 27.78B | 17.5 GB | 31 | 64.6 |
| gemma-3-27b | 27.4B | 17.2 GB | 31 | 27.2 |
| gemma-2-27b | 27.2B | 17.1 GB | 31 | 34.6 |
| Qwen 3.6 27B | 27B | 17.0 GB | 32 | 41.1 |
| Gemma 4 26B A4B | 26B | 16.4 GB | 213 | 47.9 |
| Aria 25B A3.9B | 25.3B | 16.0 GB | 219 | 64.8 |
| Mistral-Small-24B | 24B | 15.2 GB | 36 | 25.0 |
| Mistral-Small-3.1-24B | 24B | 15.2 GB | 36 | 28.8 |
| Magistral Small 24B | 24B | 15.2 GB | 36 | 47.0 |