Model field guide
deepseek-coder-6.7b-instruct
42 of 44 hardware configurations have a supported memory fit at one or more recorded quantizations. Runtime compatibility still needs verification.
Total parameters6.74B
Active parameters6.74B
Recorded context limit16,384
Architecturedense
Verified 2026-10-22 · license metadata: other · commercial use: unknown (review the terms).
Actual files, not a size shortcut.
| Quantization | Total file size | Source |
|---|---|---|
| Q4_K_M | 3.802 GiB4,082,887,648 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 | 4.457 GiB4,785,171,424 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 | 6.672 GiB7,163,751,392 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 | 6.80 GiB | fits | 15.0–30.0 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 6.80 GiB | fits | 16.7–33.3 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 6.80 GiB | fits | 16.7–33.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 6.80 GiB | fits | 30.1–60.2 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 6.80 GiB | fits | 30.1–60.2 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 6.80 GiB | fits | 30.1–60.2 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 6.80 GiB | fits | 45.1–90.1 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 6.80 GiB | fits | 60.2–120.3 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 6.80 GiB | fits | 60.2–120.3 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 6.80 GiB | fits | 117.6–235.1 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 6.80 GiB | fits | 117.6–235.1 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 6.80 GiB | fits | 117.6–235.1 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 6.80 GiB | fits | 15.0–30.0 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 6.80 GiB | fits | 30.1–60.2 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 6.80 GiB | fits | 60.2–120.3 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 6.80 GiB | fits | 11.8–23.5 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 6.80 GiB | fits | 11.8–23.5 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 6.80 GiB | fits | 11.8–23.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 6.80 GiB | fits | 26.7–53.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 6.80 GiB | fits | 26.7–53.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 6.80 GiB | fits | 26.7–53.5 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 6.80 GiB | fits | 40.2–80.3 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 6.80 GiB | fits | 53.5–107.0 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 6.80 GiB | fits | 53.5–107.0 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 6.80 GiB | fits | 80.2–160.5 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 6.80 GiB | fits | 80.2–160.5 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 6.80 GiB | fits | 35.3–70.5 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 6.80 GiB | fits | 91.7–183.4 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 6.80 GiB | fits | 28.2–56.4 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 6.80 GiB | fits | 49.4–98.8 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 6.80 GiB | fits | 70.2–140.4 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 6.80 GiB | fits | 98.8–197.5 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 6.80 GiB | fits | 43.9–87.8 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 6.80 GiB | fits | 65.8–131.7 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 6.80 GiB | fits | 87.8–175.6 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 6.80 GiB | fits | 94.1–188.1 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 6.80 GiB | fits | 175.6–351.1 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 6.80 GiB | fits | 175.6–351.1 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 6.80 GiB | fits | 94.1–188.1 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 6.80 GiB | fits | 44.7–89.3 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 6.80 GiB | fits | 25.1–50.2 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 6.80 GiB | fits | 26.7–53.5 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 6.80 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 6.80 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 | 7.46 GiB | fits | 12.8–25.6 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 7.46 GiB | fits | 14.2–28.4 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 7.46 GiB | fits | 14.2–28.4 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 7.46 GiB | fits | 25.7–51.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 7.46 GiB | fits | 25.7–51.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 7.46 GiB | fits | 25.7–51.3 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 7.46 GiB | fits | 38.5–76.9 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 7.46 GiB | fits | 51.3–102.7 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 7.46 GiB | fits | 51.3–102.7 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 7.46 GiB | fits | 100.3–200.6 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 7.46 GiB | fits | 100.3–200.6 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 7.46 GiB | fits | 100.3–200.6 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 7.46 GiB | fits | 12.8–25.6 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 7.46 GiB | fits | 25.7–51.3 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 7.46 GiB | fits | 51.3–102.7 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 7.46 GiB | fits | 10.0–20.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 7.46 GiB | fits | 10.0–20.1 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 7.46 GiB | fits | 10.0–20.1 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 7.46 GiB | fits | 22.8–45.6 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 7.46 GiB | fits | 22.8–45.6 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 7.46 GiB | fits | 22.8–45.6 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 7.46 GiB | fits | 34.3–68.5 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 7.46 GiB | fits | 45.6–91.3 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 7.46 GiB | fits | 45.6–91.3 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 7.46 GiB | fits | 68.5–136.9 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 7.46 GiB | fits | 68.5–136.9 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 7.46 GiB | fits | 30.1–60.2 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 7.46 GiB | fits | 78.2–156.5 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 7.46 GiB | fits | 24.1–48.1 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 7.46 GiB | fits | 42.1–84.3 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 7.46 GiB | fits | 59.9–119.8 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 7.46 GiB | fits | 84.3–168.5 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 7.46 GiB | fits | 37.4–74.9 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 7.46 GiB | fits | 56.2–112.3 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 7.46 GiB | fits | 74.9–149.8 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 7.46 GiB | fits | 80.2–160.5 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 7.46 GiB | fits | 149.8–299.6 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 7.46 GiB | fits | 149.8–299.6 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 7.46 GiB | fits | 80.2–160.5 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 7.46 GiB | fits | 38.1–76.2 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 7.46 GiB | fits | 21.4–42.8 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 7.46 GiB | fits | 22.8–45.6 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 7.46 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 7.46 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 | 8.5–17.1 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 9.67 GiB | fits | 9.5–19.0 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 9.67 GiB | fits | 9.5–19.0 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 9.67 GiB | fits | 17.1–34.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 9.67 GiB | fits | 17.1–34.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 9.67 GiB | fits | 17.1–34.3 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 9.67 GiB | fits | 25.7–51.4 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 9.67 GiB | fits | 34.3–68.6 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 9.67 GiB | fits | 34.3–68.6 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 9.67 GiB | fits | 67.0–134.0 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 9.67 GiB | fits | 67.0–134.0 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 9.67 GiB | fits | 67.0–134.0 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 9.67 GiB | fits | 8.5–17.1 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 9.67 GiB | fits | 17.1–34.3 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 9.67 GiB | fits | 34.3–68.6 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 9.67 GiB | fits | 6.7–13.4 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 9.67 GiB | fits | 6.7–13.4 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 9.67 GiB | fits | 6.7–13.4 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 9.67 GiB | fits | 15.2–30.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 9.67 GiB | fits | 15.2–30.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 9.67 GiB | fits | 15.2–30.5 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 9.67 GiB | fits | 22.9–45.8 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 9.67 GiB | fits | 30.5–61.0 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 9.67 GiB | fits | 30.5–61.0 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 9.67 GiB | fits | 45.7–91.5 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 9.67 GiB | fits | 45.7–91.5 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 9.67 GiB | fits | 20.1–40.2 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 9.67 GiB | fits | 52.3–104.5 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 9.67 GiB | fits | 16.1–32.2 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 9.67 GiB | fits | 28.1–56.3 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 9.67 GiB | fits | 40.0–80.0 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 9.67 GiB | fits | 56.3–112.6 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 9.67 GiB | fits | 25.0–50.0 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 9.67 GiB | fits | 37.5–75.0 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 9.67 GiB | fits | 50.0–100.1 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 9.67 GiB | fits | 53.6–107.2 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 9.67 GiB | fits | 100.1–200.1 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 9.67 GiB | fits | 100.1–200.1 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 9.67 GiB | fits | 53.6–107.2 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 9.67 GiB | fits | 25.5–50.9 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 9.67 GiB | fits | 14.3–28.6 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 9.67 GiB | fits | 15.2–30.5 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. Unknown or custom license, conflicting metadata, or unverified publisher. Review the linked license and applicable terms.
- 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 (llama); 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.