Model field guide
Qwen3-1.7B
42 of 44 hardware configurations have a supported memory fit at one or more recorded quantizations. Runtime compatibility still needs verification.
Total parameters2.03B
Active parameters2.03B
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 | 1.031 GiB1,107,409,472 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 | 1.171 GiB1,257,880,128 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 | 1.708 GiB1,834,426,944 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 | 2.47 GiB | fits | 55.3–110.5 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 2.47 GiB | fits | 61.4–122.8 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 2.47 GiB | fits | 61.4–122.8 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 2.47 GiB | fits | 110.9–221.8 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 2.47 GiB | fits | 110.9–221.8 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 2.47 GiB | fits | 110.9–221.8 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 2.47 GiB | fits | 166.2–332.3 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 2.47 GiB | fits | 221.8–443.6 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 2.47 GiB | fits | 221.8–443.6 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 2.47 GiB | fits | 433.4–866.9 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 2.47 GiB | fits | 433.4–866.9 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 2.47 GiB | fits | 433.4–866.9 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 2.47 GiB | fits | 55.3–110.5 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 2.47 GiB | fits | 110.9–221.8 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 2.47 GiB | fits | 221.8–443.6 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 2.47 GiB | fits | 43.3–86.7 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 2.47 GiB | fits | 43.3–86.7 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 2.47 GiB | fits | 43.3–86.7 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 2.47 GiB | fits | 98.6–197.2 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 2.47 GiB | fits | 98.6–197.2 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 2.47 GiB | fits | 98.6–197.2 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 2.47 GiB | fits | 148.1–296.2 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 2.47 GiB | fits | 197.2–394.4 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 2.47 GiB | fits | 197.2–394.4 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 2.47 GiB | fits | 295.8–591.7 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 2.47 GiB | fits | 295.8–591.7 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 2.47 GiB | fits | 130.0–260.1 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 2.47 GiB | fits | 338.1–676.2 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 2.47 GiB | fits | 104.0–208.1 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 2.47 GiB | fits | 182.0–364.1 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 2.47 GiB | fits | 258.9–517.8 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 2.47 GiB | fits | 364.1–728.2 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 2.47 GiB | fits | 161.8–323.6 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 2.47 GiB | fits | 242.7–485.5 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 2.47 GiB | fits | 323.6–647.3 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 2.47 GiB | fits | 346.8–693.5 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 2.47 GiB | fits | 647.3–1294.6 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 2.47 GiB | fits | 647.3–1294.6 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 2.47 GiB | fits | 346.8–693.5 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 2.47 GiB | fits | 164.7–329.4 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 2.47 GiB | fits | 92.5–184.9 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 2.47 GiB | fits | 98.6–197.2 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 2.47 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 2.47 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 | 2.61 GiB | fits | 48.7–97.3 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 2.61 GiB | fits | 54.1–108.1 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 2.61 GiB | fits | 54.1–108.1 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 2.61 GiB | fits | 97.6–195.2 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 2.61 GiB | fits | 97.6–195.2 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 2.61 GiB | fits | 97.6–195.2 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 2.61 GiB | fits | 146.3–292.6 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 2.61 GiB | fits | 195.2–390.5 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 2.61 GiB | fits | 195.2–390.5 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 2.61 GiB | fits | 381.6–763.2 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 2.61 GiB | fits | 381.6–763.2 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 2.61 GiB | fits | 381.6–763.2 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 2.61 GiB | fits | 48.7–97.3 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 2.61 GiB | fits | 97.6–195.2 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 2.61 GiB | fits | 195.2–390.5 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 2.61 GiB | fits | 38.2–76.3 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 2.61 GiB | fits | 38.2–76.3 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 2.61 GiB | fits | 38.2–76.3 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 2.61 GiB | fits | 86.8–173.6 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 2.61 GiB | fits | 86.8–173.6 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 2.61 GiB | fits | 86.8–173.6 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 2.61 GiB | fits | 130.4–260.8 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 2.61 GiB | fits | 173.6–347.3 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 2.61 GiB | fits | 173.6–347.3 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 2.61 GiB | fits | 260.4–520.9 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 2.61 GiB | fits | 260.4–520.9 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 2.61 GiB | fits | 114.5–229.0 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 2.61 GiB | fits | 297.6–595.3 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 2.61 GiB | fits | 91.6–183.2 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 2.61 GiB | fits | 160.3–320.5 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 2.61 GiB | fits | 227.9–455.9 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 2.61 GiB | fits | 320.5–641.1 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 2.61 GiB | fits | 142.5–284.9 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 2.61 GiB | fits | 213.7–427.4 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 2.61 GiB | fits | 284.9–569.8 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 2.61 GiB | fits | 305.3–610.6 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 2.61 GiB | fits | 569.8–1139.7 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 2.61 GiB | fits | 569.8–1139.7 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 2.61 GiB | fits | 305.3–610.6 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 2.61 GiB | fits | 145.0–290.0 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 2.61 GiB | fits | 81.4–162.8 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 2.61 GiB | fits | 86.8–173.6 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 2.61 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 2.61 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 | 3.15 GiB | fits | 33.4–66.7 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 3.15 GiB | fits | 37.1–74.1 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 3.15 GiB | fits | 37.1–74.1 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 3.15 GiB | fits | 66.9–133.9 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 3.15 GiB | fits | 66.9–133.9 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 3.15 GiB | fits | 66.9–133.9 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 3.15 GiB | fits | 100.3–200.6 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 3.15 GiB | fits | 133.9–267.8 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 3.15 GiB | fits | 133.9–267.8 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 3.15 GiB | fits | 261.7–523.3 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 3.15 GiB | fits | 261.7–523.3 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 3.15 GiB | fits | 261.7–523.3 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 3.15 GiB | fits | 33.4–66.7 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 3.15 GiB | fits | 66.9–133.9 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 3.15 GiB | fits | 133.9–267.8 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 3.15 GiB | fits | 26.2–52.3 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 3.15 GiB | fits | 26.2–52.3 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 3.15 GiB | fits | 26.2–52.3 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 3.15 GiB | fits | 59.5–119.1 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 3.15 GiB | fits | 59.5–119.1 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 3.15 GiB | fits | 59.5–119.1 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 3.15 GiB | fits | 89.4–178.8 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 3.15 GiB | fits | 119.1–238.1 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 3.15 GiB | fits | 119.1–238.1 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 3.15 GiB | fits | 178.6–357.2 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 3.15 GiB | fits | 178.6–357.2 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 3.15 GiB | fits | 78.5–157.0 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 3.15 GiB | fits | 204.1–408.2 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 3.15 GiB | fits | 62.8–125.6 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 3.15 GiB | fits | 109.9–219.8 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 3.15 GiB | fits | 156.3–312.6 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 3.15 GiB | fits | 219.8–439.6 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 3.15 GiB | fits | 97.7–195.4 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 3.15 GiB | fits | 146.5–293.1 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 3.15 GiB | fits | 195.4–390.7 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 3.15 GiB | fits | 209.3–418.7 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 3.15 GiB | fits | 390.7–781.5 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 3.15 GiB | fits | 390.7–781.5 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 3.15 GiB | fits | 209.3–418.7 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 3.15 GiB | fits | 99.4–198.9 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 3.15 GiB | fits | 55.8–111.6 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 3.15 GiB | fits | 59.5–119.1 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 3.15 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 3.15 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.