Can I run cogito-671b-v2.1 on a Apple M5 Max?
Not at these settings. No indexed quantization of cogito-671b-v2.1 fits Apple M5 Max at any context we compute, with q4_0 KV. The smallest shipped quantization is 138.82 GiB in weights alone, against 25.11 GiB usable. CPU offload can still run it, slowly.
Every quantization at every context
| Quant | Weights● | 4K◐ | 8K◐ | 16K◐ | 32K◐ | 64K◐ | 128K◐ |
|---|---|---|---|---|---|---|---|
| BF16 | 1250.08 GiB | 1250.8 | 1250.9 | 1251.0 | 1251.3 | 1251.9 | 1253.1 |
| Q8_0 | 664.29 GiB | 665.0 | 665.1 | 665.2 | 665.5 | 666.1 | 667.3 |
| Q6_K | 513.45 GiB | 514.1 | 514.2 | 514.4 | 514.7 | 515.3 | 516.5 |
| Q5_K_M | 443.46 GiB | 444.2 | 444.2 | 444.4 | 444.7 | 445.3 | 446.5 |
| Q5_K_S | 430.86 GiB | 431.6 | 431.6 | 431.8 | 432.1 | 432.7 | 433.9 |
| Q4_1 | 391.87 GiB | 392.6 | 392.6 | 392.8 | 393.1 | 393.7 | 394.9 |
| Q4_K_M | 377.55 GiB | 378.3 | 378.3 | 378.5 | 378.8 | 379.4 | 380.6 |
| Q4_K_S | 354.89 GiB | 355.6 | 355.7 | 355.8 | 356.1 | 356.7 | 357.9 |
| Q4_0 | 353.99 GiB | 354.7 | 354.8 | 354.9 | 355.2 | 355.8 | 357.0 |
| IQ4_NL | 353.09 GiB | 353.8 | 353.9 | 354.0 | 354.3 | 354.9 | 356.1 |
| IQ4_XS | 333.73 GiB | 334.4 | 334.5 | 334.7 | 335.0 | 335.6 | 336.8 |
| Q3_K_M | 298.44 GiB | 299.1 | 299.2 | 299.4 | 299.7 | 300.3 | 301.5 |
| Q3_K_S | 270.50 GiB | 271.2 | 271.3 | 271.4 | 271.7 | 272.3 | 273.5 |
| UD-IQ3_XXS | 254.72 GiB | 255.4 | 255.5 | 255.6 | 255.9 | 256.6 | 257.8 |
| Q2_K_L | 229.02 GiB | 229.7 | 229.8 | 230.0 | 230.3 | 230.9 | 232.1 |
| Q2_K | 228.82 GiB | 229.5 | 229.6 | 229.7 | 230.1 | 230.7 | 231.9 |
| UD-IQ2_M | 212.81 GiB | 213.5 | 213.6 | 213.7 | 214.0 | 214.7 | 215.9 |
| UD-IQ2_XXS | 201.88 GiB | 202.6 | 202.7 | 202.8 | 203.1 | 203.7 | 204.9 |
| UD-IQ1_M | 187.19 GiB | 187.9 | 188.0 | 188.1 | 188.4 | 189.0 | 190.2 |
| UD-IQ1_S | 173.11 GiB | 173.8 | 173.9 | 174.0 | 174.3 | 174.9 | 176.2 |
| IQ2_XXS | 162.59 GiB | 163.3 | 163.4 | 163.5 | 163.8 | 164.4 | 165.6 |
| UD-TQ1_0 | 150.80 GiB | 151.5 | 151.6 | 151.7 | 152.0 | 152.6 | 153.8 |
| IQ1_M | 138.82 GiB | 139.5 | 139.6 | 139.7 | 140.1 | 140.7 | 141.9 |
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.