Model field guide
Qwen3-0.6B
42 of 44 hardware configurations have a supported memory fit at one or more recorded quantizations. Runtime compatibility still needs verification.
Total parameters0.75B
Active parameters0.75B
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 |
|---|---|---|
| Q8_0 | 0.596 GiB639,446,688 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 |
| Q4_K_M | 0.369 GiB396,705,472 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 | 0.414 GiB444,415,680 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.
Q8_0: hardware comparison
| Hardware | Usable memory | Required memory | Fit estimate | Estimated generation |
|---|---|---|---|---|
| Mac mini M6 (12-core GPU) 16GB | 12.0 GiB | 2.03 GiB | fits | 95.7–191.4 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 2.03 GiB | fits | 106.3–212.7 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 2.03 GiB | fits | 106.3–212.7 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 2.03 GiB | fits | 192.0–384.1 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 2.03 GiB | fits | 192.0–384.1 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 2.03 GiB | fits | 192.0–384.1 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 2.03 GiB | fits | 287.7–575.5 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 2.03 GiB | fits | 384.1–768.2 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 2.03 GiB | fits | 384.1–768.2 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 2.03 GiB | fits | 750.6–1501.3 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 2.03 GiB | fits | 750.6–1501.3 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 2.03 GiB | fits | 750.6–1501.3 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 2.03 GiB | fits | 95.7–191.4 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 2.03 GiB | fits | 192.0–384.1 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 2.03 GiB | fits | 384.1–768.2 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 2.03 GiB | fits | 75.1–150.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 2.03 GiB | fits | 75.1–150.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 2.03 GiB | fits | 75.1–150.1 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 2.03 GiB | fits | 170.8–341.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 2.03 GiB | fits | 170.8–341.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 2.03 GiB | fits | 170.8–341.5 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 2.03 GiB | fits | 256.5–512.9 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 2.03 GiB | fits | 341.5–683.1 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 2.03 GiB | fits | 341.5–683.1 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 2.03 GiB | fits | 512.3–1024.6 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 2.03 GiB | fits | 512.3–1024.6 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 2.03 GiB | fits | 225.2–450.4 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 2.03 GiB | fits | 585.5–1171.0 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 2.03 GiB | fits | 180.2–360.3 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 2.03 GiB | fits | 315.3–630.5 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 2.03 GiB | fits | 448.4–896.8 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 2.03 GiB | fits | 630.5–1261.1 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 2.03 GiB | fits | 280.2–560.5 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 2.03 GiB | fits | 420.4–840.7 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 2.03 GiB | fits | 560.5–1121.0 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 2.03 GiB | fits | 600.5–1201.0 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 2.03 GiB | fits | 1121.0–2241.9 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 2.03 GiB | fits | 1121.0–2241.9 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 2.03 GiB | fits | 600.5–1201.0 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 2.03 GiB | fits | 285.2–570.5 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 2.03 GiB | fits | 160.1–320.3 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 2.03 GiB | fits | 170.8–341.5 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 2.03 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 2.03 GiB | Needs verification | Estimated speed unavailable |
Q4_K_M: hardware comparison
| Hardware | Usable memory | Required memory | Fit estimate | Estimated generation |
|---|---|---|---|---|
| Mac mini M6 (12-core GPU) 16GB | 12.0 GiB | 1.81 GiB | fits | 154.3–308.5 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 1.81 GiB | fits | 171.4–342.8 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 1.81 GiB | fits | 171.4–342.8 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 1.81 GiB | fits | 309.5–619.1 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 1.81 GiB | fits | 309.5–619.1 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 1.81 GiB | fits | 309.5–619.1 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 1.81 GiB | fits | 463.8–927.6 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 1.81 GiB | fits | 619.1–1238.2 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 1.81 GiB | fits | 619.1–1238.2 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 1.81 GiB | fits | 1210.0–2419.9 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 1.81 GiB | fits | 1210.0–2419.9 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 1.81 GiB | fits | 1210.0–2419.9 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 1.81 GiB | fits | 154.3–308.5 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 1.81 GiB | fits | 309.5–619.1 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 1.81 GiB | fits | 619.1–1238.2 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 1.81 GiB | fits | 121.0–242.0 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 1.81 GiB | fits | 121.0–242.0 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 1.81 GiB | fits | 121.0–242.0 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 1.81 GiB | fits | 275.3–550.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 1.81 GiB | fits | 275.3–550.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 1.81 GiB | fits | 275.3–550.5 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 1.81 GiB | fits | 413.4–826.8 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 1.81 GiB | fits | 550.5–1101.1 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 1.81 GiB | fits | 550.5–1101.1 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 1.81 GiB | fits | 825.8–1651.6 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 1.81 GiB | fits | 825.8–1651.6 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 1.81 GiB | fits | 363.0–726.0 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 1.81 GiB | fits | 943.8–1887.5 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 1.81 GiB | fits | 290.4–580.8 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 1.81 GiB | fits | 508.2–1016.4 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 1.81 GiB | fits | 722.8–1445.5 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 1.81 GiB | fits | 1016.4–2032.7 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 1.81 GiB | fits | 451.7–903.4 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 1.81 GiB | fits | 677.6–1355.2 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 1.81 GiB | fits | 903.4–1806.9 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 1.81 GiB | fits | 968.0–1935.9 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 1.81 GiB | fits | 1806.9–3613.8 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 1.81 GiB | fits | 1806.9–3613.8 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 1.81 GiB | fits | 968.0–1935.9 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 1.81 GiB | fits | 459.8–919.6 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 1.81 GiB | fits | 258.1–516.3 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 1.81 GiB | fits | 275.3–550.5 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 1.81 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 1.81 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 | 1.85 GiB | fits | 137.7–275.4 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 1.85 GiB | fits | 153.0–306.0 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 1.85 GiB | fits | 153.0–306.0 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 1.85 GiB | fits | 276.3–552.6 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 1.85 GiB | fits | 276.3–552.6 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 1.85 GiB | fits | 276.3–552.6 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 1.85 GiB | fits | 414.0–828.1 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 1.85 GiB | fits | 552.6–1105.3 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 1.85 GiB | fits | 552.6–1105.3 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 1.85 GiB | fits | 1080.1–2160.1 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 1.85 GiB | fits | 1080.1–2160.1 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 1.85 GiB | fits | 1080.1–2160.1 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 1.85 GiB | fits | 137.7–275.4 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 1.85 GiB | fits | 276.3–552.6 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 1.85 GiB | fits | 552.6–1105.3 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 1.85 GiB | fits | 108.0–216.0 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 1.85 GiB | fits | 108.0–216.0 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 1.85 GiB | fits | 108.0–216.0 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 1.85 GiB | fits | 245.7–491.4 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 1.85 GiB | fits | 245.7–491.4 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 1.85 GiB | fits | 245.7–491.4 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 1.85 GiB | fits | 369.0–738.0 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 1.85 GiB | fits | 491.4–982.9 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 1.85 GiB | fits | 491.4–982.9 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 1.85 GiB | fits | 737.1–1474.3 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 1.85 GiB | fits | 737.1–1474.3 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 1.85 GiB | fits | 324.0–648.0 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 1.85 GiB | fits | 842.5–1684.9 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 1.85 GiB | fits | 259.2–518.4 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 1.85 GiB | fits | 453.6–907.3 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 1.85 GiB | fits | 645.2–1290.3 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 1.85 GiB | fits | 907.3–1814.5 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 1.85 GiB | fits | 403.2–806.5 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 1.85 GiB | fits | 604.8–1209.7 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 1.85 GiB | fits | 806.5–1612.9 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 1.85 GiB | fits | 864.1–1728.1 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 1.85 GiB | fits | 1612.9–3225.8 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 1.85 GiB | fits | 1612.9–3225.8 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 1.85 GiB | fits | 864.1–1728.1 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 1.85 GiB | fits | 410.4–820.9 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 1.85 GiB | fits | 230.4–460.8 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 1.85 GiB | fits | 245.7–491.4 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 1.85 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 1.85 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.