Can I run Trinity-Large-TrueBase on a Radeon RX 6500 XT?
Not at these settings. No indexed quantization of Trinity-Large-TrueBase fits Radeon RX 6500 XT at any context we compute, with q8_0 KV. The smallest shipped quantization is 73.49 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◐ |
|---|---|---|---|---|---|---|---|
| Q8_0 | 394.59 GiB | 396.0 | 396.2 | 396.4 | 396.9 | 397.9 | 399.9 |
| Q6_K | 305.07 GiB | 306.5 | 306.7 | 306.9 | 307.4 | 308.4 | 310.4 |
| Q5_K_M | 263.87 GiB | 265.3 | 265.5 | 265.7 | 266.2 | 267.2 | 269.2 |
| Q5_K_S | 255.88 GiB | 257.3 | 257.5 | 257.7 | 258.2 | 259.2 | 261.2 |
| Q4_1 | 232.76 GiB | 234.2 | 234.4 | 234.6 | 235.1 | 236.1 | 238.1 |
| Q4_K_L | 225.46 GiB | 226.9 | 227.1 | 227.3 | 227.8 | 228.8 | 230.8 |
| Q4_K_M | 225.04 GiB | 226.5 | 226.6 | 226.9 | 227.4 | 228.4 | 230.4 |
| Q4_K_S | 217.12 GiB | 218.5 | 218.7 | 219.0 | 219.5 | 220.5 | 222.5 |
| Q4_0 | 213.32 GiB | 214.7 | 214.9 | 215.2 | 215.7 | 216.7 | 218.6 |
| IQ4_NL | 209.71 GiB | 211.1 | 211.3 | 211.6 | 212.1 | 213.0 | 215.0 |
| IQ4_XS | 198.19 GiB | 199.6 | 199.8 | 200.0 | 200.5 | 201.5 | 203.5 |
| I1-Q3_K_M | 176.30 GiB | 177.7 | 177.9 | 178.1 | 178.6 | 179.6 | 181.6 |
| Q3_K_L | 175.82 GiB | 177.2 | 177.4 | 177.7 | 178.2 | 179.2 | 181.1 |
| Q3_K_M | 168.74 GiB | 170.2 | 170.3 | 170.6 | 171.1 | 172.1 | 174.1 |
| IQ3_M | 168.61 GiB | 170.0 | 170.2 | 170.5 | 171.0 | 172.0 | 173.9 |
| Q3_K_S | 160.91 GiB | 162.3 | 162.5 | 162.8 | 163.2 | 164.2 | 166.2 |
| I1-IQ3_M | 160.39 GiB | 161.8 | 162.0 | 162.2 | 162.7 | 163.7 | 165.7 |
| I1-IQ3_S | 159.92 GiB | 161.3 | 161.5 | 161.8 | 162.3 | 163.3 | 165.3 |
| I1-Q3_K_S | 159.90 GiB | 161.3 | 161.5 | 161.7 | 162.2 | 163.2 | 165.2 |
| IQ3_XS | 151.27 GiB | 152.7 | 152.9 | 153.1 | 153.6 | 154.6 | 156.6 |
| I1-IQ3_XS | 150.34 GiB | 151.8 | 151.9 | 152.2 | 152.7 | 153.7 | 155.7 |
| IQ3_XXS | 146.20 GiB | 147.6 | 147.8 | 148.0 | 148.5 | 149.5 | 151.5 |
| I1-IQ3_XXS | 142.48 GiB | 143.9 | 144.1 | 144.3 | 144.8 | 145.8 | 147.8 |
| I1-Q2_K | 134.81 GiB | 136.2 | 136.4 | 136.7 | 137.2 | 138.2 | 140.1 |
| Q2_K_L | 130.00 GiB | 131.4 | 131.6 | 131.8 | 132.3 | 133.3 | 135.3 |
| Q2_K | 129.44 GiB | 130.9 | 131.0 | 131.3 | 131.8 | 132.8 | 134.8 |
| I1-Q2_K_S | 122.88 GiB | 124.3 | 124.5 | 124.7 | 125.2 | 126.2 | 128.2 |
| I1-IQ2_M | 119.77 GiB | 121.2 | 121.4 | 121.6 | 122.1 | 123.1 | 125.1 |
| IQ2_M | 116.50 GiB | 117.9 | 118.1 | 118.3 | 118.8 | 119.8 | 121.8 |
| I1-IQ2_S | 108.32 GiB | 109.7 | 109.9 | 110.2 | 110.7 | 111.7 | 113.7 |
| I1-IQ2_XS | 107.87 GiB | 109.3 | 109.5 | 109.7 | 110.2 | 111.2 | 113.2 |
| IQ2_S | 102.49 GiB | 103.9 | 104.1 | 104.3 | 104.8 | 105.8 | 107.8 |
| IQ2_XS | 102.27 GiB | 103.7 | 103.9 | 104.1 | 104.6 | 105.6 | 107.6 |
| I1-IQ2_XXS | 96.39 GiB | 97.8 | 98.0 | 98.2 | 98.7 | 99.7 | 101.7 |
| IQ2_XXS | 88.58 GiB | 90.0 | 90.2 | 90.4 | 90.9 | 91.9 | 93.9 |
| I1-IQ1_M | 82.07 GiB | 83.5 | 83.7 | 83.9 | 84.4 | 85.4 | 87.4 |
| IQ1_M | 79.29 GiB | 80.7 | 80.9 | 81.1 | 81.6 | 82.6 | 84.6 |
| IQ1_S | 76.06 GiB | 77.5 | 77.7 | 77.9 | 78.4 | 79.4 | 81.4 |
| I1-IQ1_S | 73.49 GiB | 74.9 | 75.1 | 75.3 | 75.8 | 76.8 | 78.8 |
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, most of this model's layers cache only a 4,096-token window rather than the full context.