Can I run DeepSeek-V3.1-Terminus on a Radeon RX 6500 XT?
Not at these settings. No indexed quantization of DeepSeek-V3.1-Terminus fits Radeon RX 6500 XT at any context we compute, with q4_0 KV. The smallest shipped quantization is 138.82 GiB in weights alone, against 3.72 GiB usable. CPU offload can still run it, slowly.
Every quantization at every context
| Quant | Weights● | 4K◐ | 8K◐ | 16K◐ | 32K◐ | 64K◐ | 128K◐ |
|---|---|---|---|---|---|---|---|
| F16 | 1250.09 GiB | 1251.1 | 1251.2 | 1251.4 | 1251.7 | 1252.3 | 1253.5 |
| BF16 | 1250.09 GiB | 1251.1 | 1251.2 | 1251.4 | 1251.7 | 1252.3 | 1253.5 |
| Q8_0 | 664.30 GiB | 665.4 | 665.4 | 665.6 | 665.9 | 666.5 | 667.7 |
| Q6_K | 514.51 GiB | 515.6 | 515.6 | 515.8 | 516.1 | 516.7 | 517.9 |
| Q5_K_M | 445.49 GiB | 446.5 | 446.6 | 446.8 | 447.1 | 447.7 | 448.9 |
| Q5_K_S | 431.23 GiB | 432.3 | 432.4 | 432.5 | 432.8 | 433.4 | 434.6 |
| Q4_1 | 392.12 GiB | 393.2 | 393.2 | 393.4 | 393.7 | 394.3 | 395.5 |
| Q4_K_M | 381.12 GiB | 382.2 | 382.3 | 382.4 | 382.7 | 383.3 | 384.5 |
| Q4_K_S | 367.08 GiB | 368.1 | 368.2 | 368.4 | 368.7 | 369.3 | 370.5 |
| Q4_0 | 359.88 GiB | 360.9 | 361.0 | 361.2 | 361.5 | 362.1 | 363.3 |
| IQ4_NL | 354.35 GiB | 355.4 | 355.5 | 355.6 | 355.9 | 356.5 | 357.7 |
| IQ4_XS | 335.26 GiB | 336.3 | 336.4 | 336.5 | 336.8 | 337.4 | 338.6 |
| Q3_K_M | 298.44 GiB | 299.5 | 299.6 | 299.7 | 300.0 | 300.6 | 301.8 |
| Q3_K_L | 297.75 GiB | 298.8 | 298.9 | 299.0 | 299.3 | 299.9 | 301.1 |
| IQ3_M | 286.74 GiB | 287.8 | 287.9 | 288.0 | 288.3 | 288.9 | 290.1 |
| Q3_K_S | 273.21 GiB | 274.3 | 274.3 | 274.5 | 274.8 | 275.4 | 276.6 |
| IQ3_XS | 258.11 GiB | 259.2 | 259.2 | 259.4 | 259.7 | 260.3 | 261.5 |
| UD-IQ3_XXS | 254.71 GiB | 255.8 | 255.8 | 256.0 | 256.3 | 256.9 | 258.1 |
| IQ3_XXS | 249.25 GiB | 250.3 | 250.4 | 250.5 | 250.8 | 251.4 | 252.6 |
| Q2_K_L | 229.03 GiB | 230.1 | 230.2 | 230.3 | 230.6 | 231.2 | 232.4 |
| Q2_K | 228.82 GiB | 229.9 | 230.0 | 230.1 | 230.4 | 231.0 | 232.2 |
| UD-IQ2_M | 213.17 GiB | 214.2 | 214.3 | 214.4 | 214.7 | 215.4 | 216.6 |
| UD-IQ2_XXS | 202.23 GiB | 203.3 | 203.4 | 203.5 | 203.8 | 204.4 | 205.6 |
| IQ2_M | 200.27 GiB | 201.3 | 201.4 | 201.5 | 201.9 | 202.5 | 203.7 |
| UD-IQ1_M | 187.19 GiB | 188.2 | 188.3 | 188.5 | 188.8 | 189.4 | 190.6 |
| IQ2_XS | 181.82 GiB | 182.9 | 183.0 | 183.1 | 183.4 | 184.0 | 185.2 |
| IQ2_S | 176.61 GiB | 177.7 | 177.7 | 177.9 | 178.2 | 178.8 | 180.0 |
| UD-IQ1_S | 173.84 GiB | 174.9 | 175.0 | 175.1 | 175.4 | 176.0 | 177.2 |
| IQ2_XXS | 162.59 GiB | 163.6 | 163.7 | 163.9 | 164.2 | 164.8 | 166.0 |
| UD-TQ1_0 | 151.97 GiB | 153.0 | 153.1 | 153.2 | 153.5 | 154.2 | 155.4 |
| IQ1_M | 138.82 GiB | 139.9 | 140.0 | 140.1 | 140.4 | 141.0 | 142.2 |
Figures are GiB of total memory: weights plus KV cache plus compute buffer and backend overhead. Weights and KV are near-exact; the overhead term is modeled. Hover any cell for the breakdown.
Why other calculators disagree
A parameters × bits ÷ 8 estimate ignores two things that dominate at long context. First, the weights themselves are not the nominal rate — quantizations are mixtures, so the real file is consistently larger than the label implies. Second, this model uses latent attention and allocates no V cache at all, so any formula reading num_key_value_heads overstates its cache by more than an order of magnitude.