Model field guide
DeepSeek-R1-Distill-Qwen-14B
42 of 44 hardware configurations have a supported memory fit at one or more recorded quantizations. Runtime compatibility still needs verification.
Total parameters14.77B
Active parameters14.77B
Recorded context limit131,072
Architecturedense
Verified 2026-10-22 · license metadata: mit · commercial use: yes (review the terms).
Actual files, not a size shortcut.
| Quantization | Total file size | Source |
|---|---|---|
| Q4_K_M | 8.371 GiB8,988,109,984 bytes; 1 file(s)Sum of exact file byte sizes in the repository listing at the recorded commit; every declared shard is present. Auxiliary vision projector and speculative-decoding files are excluded. Labels follow publisher filenames; mixed-precision expert tensors may remain in a differently labeled file, so the estimator uses measured bytes rather than assumed bits per weight. | Pinned file recordVerified 2026-10-22 |
| Q5_K_M | 9.787 GiB10,508,872,864 bytes; 1 file(s)Sum of exact file byte sizes in the repository listing at the recorded commit; every declared shard is present. Auxiliary vision projector and speculative-decoding files are excluded. Labels follow publisher filenames; mixed-precision expert tensors may remain in a differently labeled file, so the estimator uses measured bytes rather than assumed bits per weight. | Pinned file recordVerified 2026-10-22 |
| Q8_0 | 14.623 GiB15,701,597,344 bytes; 1 file(s)Sum of exact file byte sizes in the repository listing at the recorded commit; every declared shard is present. Auxiliary vision projector and speculative-decoding files are excluded. Labels follow publisher filenames; mixed-precision expert tensors may remain in a differently labeled file, so the estimator uses measured bytes rather than assumed bits per weight. | Pinned file recordVerified 2026-10-22 |
| FP16 | 27.518 GiB29,547,715,744 bytes; 1 file(s)Sum of exact file byte sizes in the repository listing at the recorded commit; every declared shard is present. Auxiliary vision projector and speculative-decoding files are excluded. Labels follow publisher filenames; mixed-precision expert tensors may remain in a differently labeled file, so the estimator uses measured bytes rather than assumed bits per weight. | Pinned file recordVerified 2026-10-22 |
The hardware picture.
Q4_K_M: hardware comparison
| Hardware | Usable memory | Required memory | Fit estimate | Estimated generation |
|---|---|---|---|---|
| Mac mini M6 (12-core GPU) 16GB | 12.0 GiB | 10.12 GiB | fits | 6.8–13.6 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 10.12 GiB | fits | 7.6–15.1 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 10.12 GiB | fits | 7.6–15.1 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 10.12 GiB | fits | 13.7–27.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 10.12 GiB | fits | 13.7–27.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 10.12 GiB | fits | 13.7–27.3 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 10.12 GiB | fits | 20.5–40.9 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 10.12 GiB | fits | 27.3–54.6 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 10.12 GiB | fits | 27.3–54.6 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 10.12 GiB | fits | 53.4–106.8 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 10.12 GiB | fits | 53.4–106.8 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 10.12 GiB | fits | 53.4–106.8 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 10.12 GiB | fits | 6.8–13.6 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 10.12 GiB | fits | 13.7–27.3 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 10.12 GiB | fits | 27.3–54.6 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 10.12 GiB | fits | 5.3–10.7 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 10.12 GiB | fits | 5.3–10.7 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 10.12 GiB | fits | 5.3–10.7 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 10.12 GiB | fits | 12.1–24.3 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 10.12 GiB | fits | 12.1–24.3 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 10.12 GiB | fits | 12.1–24.3 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 10.12 GiB | fits | 18.2–36.5 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 10.12 GiB | fits | 24.3–48.6 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 10.12 GiB | fits | 24.3–48.6 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 10.12 GiB | fits | 36.4–72.9 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 10.12 GiB | fits | 36.4–72.9 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 10.12 GiB | borderline | 16.0–32.0 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 10.12 GiB | fits | 41.7–83.3 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 10.12 GiB | fits | 12.8–25.6 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 10.12 GiB | borderline | 22.4–44.9 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 10.12 GiB | fits | 31.9–63.8 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 10.12 GiB | fits | 44.9–89.7 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 10.12 GiB | fits | 19.9–39.9 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 10.12 GiB | borderline | 29.9–59.8 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 10.12 GiB | fits | 39.9–79.7 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 10.12 GiB | fits | 42.7–85.4 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 10.12 GiB | fits | 79.7–159.5 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 10.12 GiB | fits | 79.7–159.5 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 10.12 GiB | fits | 42.7–85.4 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 10.12 GiB | borderline | 20.3–40.6 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 10.12 GiB | fits | 11.4–22.8 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 10.12 GiB | fits | 12.1–24.3 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 10.12 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 10.12 GiB | Needs verification | Estimated speed unavailable |
Q5_K_M: hardware comparison
| Hardware | Usable memory | Required memory | Fit estimate | Estimated generation |
|---|---|---|---|---|
| Mac mini M6 (12-core GPU) 16GB | 12.0 GiB | 11.54 GiB | borderline | 5.8–11.6 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 11.54 GiB | fits | 6.5–12.9 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 11.54 GiB | fits | 6.5–12.9 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 11.54 GiB | fits | 11.7–23.4 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 11.54 GiB | fits | 11.7–23.4 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 11.54 GiB | fits | 11.7–23.4 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 11.54 GiB | fits | 17.5–35.0 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 11.54 GiB | fits | 23.4–46.7 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 11.54 GiB | fits | 23.4–46.7 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 11.54 GiB | fits | 45.7–91.4 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 11.54 GiB | fits | 45.7–91.4 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 11.54 GiB | fits | 45.7–91.4 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 11.54 GiB | fits | 5.8–11.6 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 11.54 GiB | fits | 11.7–23.4 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 11.54 GiB | fits | 23.4–46.7 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 11.54 GiB | borderline | 4.6–9.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 11.54 GiB | fits | 4.6–9.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 11.54 GiB | fits | 4.6–9.1 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 11.54 GiB | fits | 10.4–20.8 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 11.54 GiB | fits | 10.4–20.8 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 11.54 GiB | fits | 10.4–20.8 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 11.54 GiB | fits | 15.6–31.2 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 11.54 GiB | fits | 20.8–41.6 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 11.54 GiB | fits | 20.8–41.6 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 11.54 GiB | fits | 31.2–62.3 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 11.54 GiB | fits | 31.2–62.3 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 11.54 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 11.54 GiB | fits | 35.6–71.3 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 11.54 GiB | fits | 11.0–21.9 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 11.54 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 11.54 GiB | fits | 27.3–54.6 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 11.54 GiB | fits | 38.4–76.7 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 11.54 GiB | fits | 17.1–34.1 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 11.54 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 11.54 GiB | fits | 34.1–68.2 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 11.54 GiB | fits | 36.5–73.1 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 11.54 GiB | fits | 68.2–136.4 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 11.54 GiB | fits | 68.2–136.4 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 11.54 GiB | fits | 36.5–73.1 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 11.54 GiB | doesn't fit | Estimated speed unavailable |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 11.54 GiB | fits | 9.7–19.5 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 11.54 GiB | fits | 10.4–20.8 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 11.54 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 11.54 GiB | Needs verification | Estimated speed unavailable |
Q8_0: hardware comparison
| Hardware | Usable memory | Required memory | Fit estimate | Estimated generation |
|---|---|---|---|---|
| Mac mini M6 (12-core GPU) 16GB | 12.0 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 16.37 GiB | borderline | 4.3–8.7 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 16.37 GiB | fits | 4.3–8.7 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 16.37 GiB | borderline | 7.8–15.6 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 16.37 GiB | fits | 7.8–15.6 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 16.37 GiB | fits | 7.8–15.6 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 16.37 GiB | fits | 11.7–23.4 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 16.37 GiB | fits | 15.6–31.3 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 16.37 GiB | fits | 15.6–31.3 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 16.37 GiB | fits | 30.6–61.1 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 16.37 GiB | fits | 30.6–61.1 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 16.37 GiB | fits | 30.6–61.1 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 16.37 GiB | borderline | 3.9–7.8 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 16.37 GiB | fits | 7.8–15.6 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 16.37 GiB | fits | 15.6–31.3 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 16.37 GiB | borderline | 3.1–6.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 16.37 GiB | fits | 3.1–6.1 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 16.37 GiB | borderline | 7.0–13.9 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 16.37 GiB | fits | 7.0–13.9 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 16.37 GiB | fits | 7.0–13.9 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 16.37 GiB | fits | 10.4–20.9 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 16.37 GiB | fits | 13.9–27.8 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 16.37 GiB | fits | 13.9–27.8 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 16.37 GiB | fits | 20.9–41.7 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 16.37 GiB | fits | 20.9–41.7 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 16.37 GiB | fits | 23.8–47.7 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 16.37 GiB | fits | 25.7–51.4 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 16.37 GiB | fits | 45.7–91.3 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 16.37 GiB | fits | 45.7–91.3 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 16.37 GiB | fits | 24.5–48.9 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 16.37 GiB | doesn't fit | Estimated speed unavailable |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 16.37 GiB | fits | 6.5–13.0 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 16.37 GiB | fits | 7.0–13.9 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 16.37 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 16.37 GiB | Needs verification | Estimated speed unavailable |
FP16: hardware comparison
| Hardware | Usable memory | Required memory | Fit estimate | Estimated generation |
|---|---|---|---|---|
| Mac mini M6 (12-core GPU) 16GB | 12.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 29.27 GiB | fits | 4.2–8.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 29.27 GiB | fits | 4.2–8.3 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 29.27 GiB | fits | 8.3–16.6 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 29.27 GiB | fits | 8.3–16.6 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 29.27 GiB | fits | 16.2–32.5 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 29.27 GiB | fits | 16.2–32.5 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 29.27 GiB | fits | 16.2–32.5 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 29.27 GiB | fits | 4.2–8.3 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 29.27 GiB | fits | 8.3–16.6 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 29.27 GiB | fits | 3.7–7.4 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 29.27 GiB | fits | 3.7–7.4 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 29.27 GiB | fits | 7.4–14.8 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 29.27 GiB | fits | 7.4–14.8 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 29.27 GiB | fits | 11.1–22.2 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 29.27 GiB | fits | 11.1–22.2 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 29.27 GiB | fits | 24.3–48.5 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 29.27 GiB | fits | 13.0–26.0 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 29.27 GiB | doesn't fit | Estimated speed unavailable |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 29.27 GiB | fits | 3.5–6.9 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 29.27 GiB | fits | 3.7–7.4 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 29.27 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 29.27 GiB | Needs verification | Estimated speed unavailable |
A “fits” result checks estimated memory only. “Needs verification” preserves missing cache, vision, or placement information. All speed figures are estimated from the published bandwidth formula.
Field-level sources and verification dates
- id: Official source · verified 2026-10-22. Lowercase URL slug derived from the upstream repository ID; baseModel retains the exact Hugging Face identifier.
- name: Official source · verified 2026-10-22
- baseModel: Official source · verified 2026-10-22
- downloads: Official source · verified 2026-10-22
- tasks: Official source · verified 2026-10-22. Chat denotes a text-generating model, including base models that may require a chat template or instruction tuning. Code label is inferred from the repository model-family name. Vision uses pipeline metadata or vision_config.
- license: Official source · verified 2026-10-22
- commercialUse: Official source · verified 2026-10-22. Official upstream organization metadata identifies a permissive standard license. Commercial use is permitted subject to the license terms, notices, and applicable restrictions; this is a metadata-based classification, not an individualized legal approval.
- license_url: Official source · verified 2026-10-22. Pinned license file confirmed in repository listing.
- architecture: Official source · verified 2026-10-22. Classification from model_type and expert/state-space configuration fields (qwen2); hybrid classification takes precedence over expert count.
- parametersB: Official source · verified 2026-10-22. Exact safetensors parameter total reported by the Hugging Face API, divided by 1e9.
- activeParametersB: Official source · verified 2026-10-22. Dense model: all parameters are included. This is not a runtime FLOP measurement.
- contextLength: Official source · verified 2026-10-22. Configured maximum token positions; not a guarantee of runtime support or quality at that length. No speculative RoPE scaling applied.
- kvCache: Official source · verified 2026-10-22. Standard attention KV shape from num_hidden_layers, num_key_value_heads, and head_dim or hidden_size / num_attention_heads; FP16 cache bytes are a separate estimator choice.
- licenseStandard: Official source · verified 2026-10-22. Official standard license text supporting the permissive-license classification; model applicability is identified separately by upstream metadata.