Model field guide
Qwen3-8B
42 of 44 hardware configurations have a supported memory fit at one or more recorded quantizations. Runtime compatibility still needs verification.
Total parameters8.19B
Active parameters8.19B
Recorded context limit40,960
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 | 4.682 GiB5,027,783,488 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 | 5.449 GiB5,851,112,224 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 | 8.111 GiB8,709,518,112 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 | 6.24 GiB | fits | 12.2–24.3 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 6.24 GiB | fits | 13.5–27.0 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 6.24 GiB | fits | 13.5–27.0 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 6.24 GiB | fits | 24.4–48.8 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 6.24 GiB | fits | 24.4–48.8 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 6.24 GiB | fits | 24.4–48.8 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 6.24 GiB | fits | 36.6–73.2 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 6.24 GiB | fits | 48.8–97.7 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 6.24 GiB | fits | 48.8–97.7 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 6.24 GiB | fits | 95.5–190.9 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 6.24 GiB | fits | 95.5–190.9 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 6.24 GiB | fits | 95.5–190.9 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 6.24 GiB | fits | 12.2–24.3 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 6.24 GiB | fits | 24.4–48.8 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 6.24 GiB | fits | 48.8–97.7 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 6.24 GiB | fits | 9.5–19.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 6.24 GiB | fits | 9.5–19.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 6.24 GiB | fits | 9.5–19.1 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 6.24 GiB | fits | 21.7–43.4 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 6.24 GiB | fits | 21.7–43.4 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 6.24 GiB | fits | 21.7–43.4 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 6.24 GiB | fits | 32.6–65.2 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 6.24 GiB | fits | 43.4–86.9 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 6.24 GiB | fits | 43.4–86.9 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 6.24 GiB | fits | 65.2–130.3 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 6.24 GiB | fits | 65.2–130.3 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 6.24 GiB | fits | 28.6–57.3 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 6.24 GiB | fits | 74.5–148.9 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 6.24 GiB | fits | 22.9–45.8 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 6.24 GiB | fits | 40.1–80.2 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 6.24 GiB | fits | 57.0–114.1 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 6.24 GiB | fits | 80.2–160.4 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 6.24 GiB | fits | 35.6–71.3 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 6.24 GiB | fits | 53.5–106.9 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 6.24 GiB | fits | 71.3–142.6 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 6.24 GiB | fits | 76.4–152.8 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 6.24 GiB | fits | 142.6–285.1 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 6.24 GiB | fits | 142.6–285.1 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 6.24 GiB | fits | 76.4–152.8 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 6.24 GiB | fits | 36.3–72.6 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 6.24 GiB | fits | 20.4–40.7 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 6.24 GiB | fits | 21.7–43.4 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 6.24 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 6.24 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 | 7.01 GiB | fits | 10.5–20.9 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 7.01 GiB | fits | 11.6–23.2 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 7.01 GiB | fits | 11.6–23.2 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 7.01 GiB | fits | 21.0–42.0 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 7.01 GiB | fits | 21.0–42.0 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 7.01 GiB | fits | 21.0–42.0 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 7.01 GiB | fits | 31.4–62.9 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 7.01 GiB | fits | 42.0–83.9 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 7.01 GiB | fits | 42.0–83.9 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 7.01 GiB | fits | 82.0–164.1 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 7.01 GiB | fits | 82.0–164.1 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 7.01 GiB | fits | 82.0–164.1 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 7.01 GiB | fits | 10.5–20.9 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 7.01 GiB | fits | 21.0–42.0 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 7.01 GiB | fits | 42.0–83.9 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 7.01 GiB | fits | 8.2–16.4 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 7.01 GiB | fits | 8.2–16.4 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 7.01 GiB | fits | 8.2–16.4 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 7.01 GiB | fits | 18.7–37.3 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 7.01 GiB | fits | 18.7–37.3 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 7.01 GiB | fits | 18.7–37.3 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 7.01 GiB | fits | 28.0–56.1 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 7.01 GiB | fits | 37.3–74.7 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 7.01 GiB | fits | 37.3–74.7 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 7.01 GiB | fits | 56.0–112.0 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 7.01 GiB | fits | 56.0–112.0 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 7.01 GiB | fits | 24.6–49.2 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 7.01 GiB | fits | 64.0–128.0 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 7.01 GiB | fits | 19.7–39.4 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 7.01 GiB | fits | 34.5–68.9 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 7.01 GiB | fits | 49.0–98.0 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 7.01 GiB | fits | 68.9–137.8 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 7.01 GiB | fits | 30.6–61.3 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 7.01 GiB | fits | 45.9–91.9 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 7.01 GiB | fits | 61.3–122.5 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 7.01 GiB | fits | 65.6–131.3 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 7.01 GiB | fits | 122.5–245.0 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 7.01 GiB | fits | 122.5–245.0 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 7.01 GiB | fits | 65.6–131.3 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 7.01 GiB | fits | 31.2–62.3 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 7.01 GiB | fits | 17.5–35.0 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 7.01 GiB | fits | 18.7–37.3 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 7.01 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 7.01 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 | 9.67 GiB | fits | 7.0–14.1 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 9.67 GiB | fits | 7.8–15.6 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 9.67 GiB | fits | 7.8–15.6 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 9.67 GiB | fits | 14.1–28.2 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 9.67 GiB | fits | 14.1–28.2 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 9.67 GiB | fits | 14.1–28.2 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 9.67 GiB | fits | 21.1–42.3 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 9.67 GiB | fits | 28.2–56.4 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 9.67 GiB | fits | 28.2–56.4 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 9.67 GiB | fits | 55.1–110.2 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 9.67 GiB | fits | 55.1–110.2 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 9.67 GiB | fits | 55.1–110.2 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 9.67 GiB | fits | 7.0–14.1 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 9.67 GiB | fits | 14.1–28.2 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 9.67 GiB | fits | 28.2–56.4 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 9.67 GiB | fits | 5.5–11.0 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 9.67 GiB | fits | 5.5–11.0 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 9.67 GiB | fits | 5.5–11.0 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 9.67 GiB | fits | 12.5–25.1 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 9.67 GiB | fits | 12.5–25.1 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 9.67 GiB | fits | 12.5–25.1 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 9.67 GiB | fits | 18.8–37.7 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 9.67 GiB | fits | 25.1–50.2 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 9.67 GiB | fits | 25.1–50.2 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 9.67 GiB | fits | 37.6–75.2 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 9.67 GiB | fits | 37.6–75.2 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 9.67 GiB | fits | 16.5–33.1 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 9.67 GiB | fits | 43.0–86.0 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 9.67 GiB | fits | 13.2–26.5 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 9.67 GiB | fits | 23.1–46.3 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 9.67 GiB | fits | 32.9–65.8 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 9.67 GiB | fits | 46.3–92.6 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 9.67 GiB | fits | 20.6–41.2 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 9.67 GiB | fits | 30.9–61.7 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 9.67 GiB | fits | 41.2–82.3 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 9.67 GiB | fits | 44.1–88.2 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 9.67 GiB | fits | 82.3–164.6 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 9.67 GiB | fits | 82.3–164.6 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 9.67 GiB | fits | 44.1–88.2 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 9.67 GiB | fits | 20.9–41.9 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 9.67 GiB | fits | 11.8–23.5 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 9.67 GiB | fits | 12.5–25.1 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 9.67 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 9.67 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 (qwen3); 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.