Radeon RX 6950 XT Price & Used Prices: Which Local LLMs Can It Run?
The Radeon RX 6950 XT has 16GB of GDDR6 memory with 576 GB/s of bandwidth. No used-price data yet. At Q4 quantization it runs models up to 14B parameters at roughly 32 tokens/s.
Radeon RX 6950 XT used price history
Full Radeon RX 6950 XT specifications
What LLMs can the Radeon RX 6950 XT run?
Versions released since 2026 with up to 50B parameters| Model | 2-bit | 4-bit | 8-bit | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Fits | Speed t/s | Context | Fits | Speed t/s | Context | Fits | Speed t/s | Context | |
| GemmaGemma 4 E4B | ✓ | 80 | 128K | ✓ | 56.3 | 128K | ✓ | 31.9 | 32K |
| QwenQwen3.5 9B | ✓ | 65.5 | 32K | ✓ | 46.2 | 32K | ✓ | 26.3 | 32K |
| GemmaGemma 4 12B | ✓ | 45.9 | 8K | ✓ | 33.7 | 8K | ✗ | — | — |
| GemmaGemma 4 26B A4B | ✓ | 79.8 | 8K | Offload | 34.2 | — | Offload | 20.8 | — |
| QwenQwen3.6 27B | ✓ | 24.4 | 8K | ✗ | — | — | ✗ | — | — |
| QwenQwen3.8 27B | ✓ | 24.4 | 8K | ✗ | — | — | ✗ | — | — |
| GLMGLM 4.7 Flash | ✓ | 115.3 | 32K | Offload | 35.7 | — | Offload | 20.8 | — |
| GemmaGemma 4 31B | ✗ | — | — | ✗ | — | — | ✗ | — | — |
| QwenQwen3.6 35B A3B | ✓ | 110.6 | 8K | Offload | 47 | — | Offload | 28.4 | — |
Fits when weights + KV cache + runtime overhead is at or below usable memory, single card. "Offload" on MoE models means it runs with expert weights in system RAM (only attention layers and KV cache stay in VRAM); that speed assumes 70 GB/s RAM bandwidth. The context column is the largest tier that fits.
Prices by platform
Buy links may carry affiliate tags; they do not change the price you pay.
FAQ
How much VRAM does the Radeon RX 6950 XT have?
The Radeon RX 6950 XT has 16GB of GDDR6 memory with 576 GB/s of bandwidth.
Can the Radeon RX 6950 XT run a 70B model?
Not on a single card. At Q4_K_M with an 8K context a 70B dense model needs about 43GB, more than the Radeon RX 6950 XT's 16GB.
How much does a used Radeon RX 6950 XT cost?
No used-price data yet; it will appear here once the feed is live.