Model field guide
granite-guardian-4.1-8b
42 of 44 hardware configurations have a supported memory fit at one or more recorded quantizations. Runtime compatibility still needs verification.
Total parameters8.38B
Active parameters8.38B
Recorded context limit131,072
Architecturedense
Verified 2026-10-22 · license metadata: apache-2.0 · commercial use: yes (review the terms).
Actual files, not a size shortcut.
| Quantization | Total file size | Source |
|---|---|---|
| Q4_K_M | 4.765 GiB5,116,703,808 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 | 5.561 GiB5,971,293,248 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 | 8.297 GiB8,908,878,912 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 | 6.39 GiB | fits | 12.0–23.9 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 6.39 GiB | fits | 13.3–26.6 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 6.39 GiB | fits | 13.3–26.6 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 6.39 GiB | fits | 24.0–48.0 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 6.39 GiB | fits | 24.0–48.0 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 6.39 GiB | fits | 24.0–48.0 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 6.39 GiB | fits | 36.0–71.9 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 6.39 GiB | fits | 48.0–96.0 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 6.39 GiB | fits | 48.0–96.0 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 6.39 GiB | fits | 93.8–187.6 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 6.39 GiB | fits | 93.8–187.6 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 6.39 GiB | fits | 93.8–187.6 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 6.39 GiB | fits | 12.0–23.9 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 6.39 GiB | fits | 24.0–48.0 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 6.39 GiB | fits | 48.0–96.0 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 6.39 GiB | fits | 9.4–18.8 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 6.39 GiB | fits | 9.4–18.8 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 6.39 GiB | fits | 9.4–18.8 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 6.39 GiB | fits | 21.3–42.7 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 6.39 GiB | fits | 21.3–42.7 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 6.39 GiB | fits | 21.3–42.7 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 6.39 GiB | fits | 32.1–64.1 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 6.39 GiB | fits | 42.7–85.4 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 6.39 GiB | fits | 42.7–85.4 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 6.39 GiB | fits | 64.0–128.1 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 6.39 GiB | fits | 64.0–128.1 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 6.39 GiB | fits | 28.1–56.3 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 6.39 GiB | fits | 73.2–146.3 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 6.39 GiB | fits | 22.5–45.0 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 6.39 GiB | fits | 39.4–78.8 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 6.39 GiB | fits | 56.0–112.1 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 6.39 GiB | fits | 78.8–157.6 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 6.39 GiB | fits | 35.0–70.0 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 6.39 GiB | fits | 52.5–105.1 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 6.39 GiB | fits | 70.0–140.1 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 6.39 GiB | fits | 75.0–150.1 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 6.39 GiB | fits | 140.1–280.2 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 6.39 GiB | fits | 140.1–280.2 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 6.39 GiB | fits | 75.0–150.1 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 6.39 GiB | fits | 35.6–71.3 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 6.39 GiB | fits | 20.0–40.0 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 6.39 GiB | fits | 21.3–42.7 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 6.39 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 6.39 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 | 7.19 GiB | fits | 10.2–20.5 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 7.19 GiB | fits | 11.4–22.8 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 7.19 GiB | fits | 11.4–22.8 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 7.19 GiB | fits | 20.6–41.1 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 7.19 GiB | fits | 20.6–41.1 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 7.19 GiB | fits | 20.6–41.1 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 7.19 GiB | fits | 30.8–61.6 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 7.19 GiB | fits | 41.1–82.3 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 7.19 GiB | fits | 41.1–82.3 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 7.19 GiB | fits | 80.4–160.8 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 7.19 GiB | fits | 80.4–160.8 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 7.19 GiB | fits | 80.4–160.8 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 7.19 GiB | fits | 10.2–20.5 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 7.19 GiB | fits | 20.6–41.1 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 7.19 GiB | fits | 41.1–82.3 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 7.19 GiB | fits | 8.0–16.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 7.19 GiB | fits | 8.0–16.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 7.19 GiB | fits | 8.0–16.1 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 7.19 GiB | fits | 18.3–36.6 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 7.19 GiB | fits | 18.3–36.6 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 7.19 GiB | fits | 18.3–36.6 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 7.19 GiB | fits | 27.5–54.9 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 7.19 GiB | fits | 36.6–73.1 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 7.19 GiB | fits | 36.6–73.1 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 7.19 GiB | fits | 54.9–109.7 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 7.19 GiB | fits | 54.9–109.7 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 7.19 GiB | fits | 24.1–48.2 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 7.19 GiB | fits | 62.7–125.4 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 7.19 GiB | fits | 19.3–38.6 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 7.19 GiB | fits | 33.8–67.5 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 7.19 GiB | fits | 48.0–96.0 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 7.19 GiB | fits | 67.5–135.0 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 7.19 GiB | fits | 30.0–60.0 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 7.19 GiB | fits | 45.0–90.0 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 7.19 GiB | fits | 60.0–120.0 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 7.19 GiB | fits | 64.3–128.6 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 7.19 GiB | fits | 120.0–240.1 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 7.19 GiB | fits | 120.0–240.1 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 7.19 GiB | fits | 64.3–128.6 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 7.19 GiB | fits | 30.5–61.1 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 7.19 GiB | fits | 17.1–34.3 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 7.19 GiB | fits | 18.3–36.6 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 7.19 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 7.19 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 | 9.92 GiB | fits | 6.9–13.7 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 9.92 GiB | fits | 7.6–15.3 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 9.92 GiB | fits | 7.6–15.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 9.92 GiB | fits | 13.8–27.6 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 9.92 GiB | fits | 13.8–27.6 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 9.92 GiB | fits | 13.8–27.6 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 9.92 GiB | fits | 20.7–41.3 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 9.92 GiB | fits | 27.6–55.1 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 9.92 GiB | fits | 27.6–55.1 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 9.92 GiB | fits | 53.9–107.8 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 9.92 GiB | fits | 53.9–107.8 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 9.92 GiB | fits | 53.9–107.8 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 9.92 GiB | fits | 6.9–13.7 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 9.92 GiB | fits | 13.8–27.6 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 9.92 GiB | fits | 27.6–55.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 9.92 GiB | fits | 5.4–10.8 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 9.92 GiB | fits | 5.4–10.8 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 9.92 GiB | fits | 5.4–10.8 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 9.92 GiB | fits | 12.3–24.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 9.92 GiB | fits | 12.3–24.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 9.92 GiB | fits | 12.3–24.5 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 9.92 GiB | fits | 18.4–36.8 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 9.92 GiB | fits | 24.5–49.0 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 9.92 GiB | fits | 24.5–49.0 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 9.92 GiB | fits | 36.8–73.5 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 9.92 GiB | fits | 36.8–73.5 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 9.92 GiB | borderline | 16.2–32.3 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 9.92 GiB | fits | 42.0–84.1 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 9.92 GiB | fits | 12.9–25.9 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 9.92 GiB | borderline | 22.6–45.3 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 9.92 GiB | fits | 32.2–64.4 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 9.92 GiB | fits | 45.3–90.5 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 9.92 GiB | fits | 20.1–40.2 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 9.92 GiB | borderline | 30.2–60.3 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 9.92 GiB | fits | 40.2–80.5 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 9.92 GiB | fits | 43.1–86.2 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 9.92 GiB | fits | 80.5–160.9 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 9.92 GiB | fits | 80.5–160.9 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 9.92 GiB | fits | 43.1–86.2 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 9.92 GiB | borderline | 20.5–40.9 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 9.92 GiB | fits | 11.5–23.0 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 9.92 GiB | fits | 12.3–24.5 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 9.92 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 9.92 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. No recognized standalone license file; linked pinned model card.
- architecture: Official source · verified 2026-10-22. Classification from model_type and expert/state-space configuration fields (granite); 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.