Model field guide
Qwen2.5-Coder-7B-Instruct
42 of 44 hardware configurations have a supported memory fit at one or more recorded quantizations. Runtime compatibility still needs verification.
Total parameters7.62B
Active parameters7.62B
Recorded context limit32,768
Architecturedense
Verified 2026-10-22 · license metadata: apache-2.0 · commercial use: yes (review the terms).
- Qwen/Qwen2.5-Coder-7B-Instruct-GGUF: omitted FP16 file set with incomplete shards, duplicate paths, or unavailable sizes.
- Qwen/Qwen2.5-Coder-7B-Instruct-GGUF: omitted Q4_K_M file set with incomplete shards, duplicate paths, or unavailable sizes.
- Qwen/Qwen2.5-Coder-7B-Instruct-GGUF: omitted Q5_K_M file set with incomplete shards, duplicate paths, or unavailable sizes.
- Qwen/Qwen2.5-Coder-7B-Instruct-GGUF: omitted Q8_0 file set with incomplete shards, duplicate paths, or unavailable sizes.
Actual files, not a size shortcut.
| Quantization | Total file size | Source |
|---|---|---|
| Q4_K_M | 4.361 GiB4,683,074,048 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 | 7.542 GiB8,098,525,696 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 | 5.58 GiB | fits | 13.1–26.1 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 5.58 GiB | fits | 14.5–29.0 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 5.58 GiB | fits | 14.5–29.0 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 5.58 GiB | fits | 26.2–52.4 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 5.58 GiB | fits | 26.2–52.4 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 5.58 GiB | fits | 26.2–52.4 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 5.58 GiB | fits | 39.3–78.6 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 5.58 GiB | fits | 52.4–104.9 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 5.58 GiB | fits | 52.4–104.9 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 5.58 GiB | fits | 102.5–205.0 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 5.58 GiB | fits | 102.5–205.0 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 5.58 GiB | fits | 102.5–205.0 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 5.58 GiB | fits | 13.1–26.1 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 5.58 GiB | fits | 26.2–52.4 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 5.58 GiB | fits | 52.4–104.9 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 5.58 GiB | fits | 10.2–20.5 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 5.58 GiB | fits | 10.2–20.5 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 5.58 GiB | fits | 10.2–20.5 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 5.58 GiB | fits | 23.3–46.6 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 5.58 GiB | fits | 23.3–46.6 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 5.58 GiB | fits | 23.3–46.6 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 5.58 GiB | fits | 35.0–70.0 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 5.58 GiB | fits | 46.6–93.3 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 5.58 GiB | fits | 46.6–93.3 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 5.58 GiB | fits | 70.0–139.9 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 5.58 GiB | fits | 70.0–139.9 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 5.58 GiB | fits | 30.7–61.5 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 5.58 GiB | fits | 79.9–159.9 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 5.58 GiB | fits | 24.6–49.2 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 5.58 GiB | fits | 43.0–86.1 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 5.58 GiB | fits | 61.2–122.4 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 5.58 GiB | fits | 86.1–172.2 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 5.58 GiB | fits | 38.3–76.5 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 5.58 GiB | fits | 57.4–114.8 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 5.58 GiB | fits | 76.5–153.1 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 5.58 GiB | fits | 82.0–164.0 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 5.58 GiB | fits | 153.1–306.1 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 5.58 GiB | fits | 153.1–306.1 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 5.58 GiB | fits | 82.0–164.0 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 5.58 GiB | fits | 38.9–77.9 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 5.58 GiB | fits | 21.9–43.7 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 5.58 GiB | fits | 23.3–46.6 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 5.58 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 5.58 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 | 8.76 GiB | fits | 7.6–15.1 estimated tokens/s |
| Mac mini M6 (12-core GPU) 24GB | 18.0 GiB | 8.76 GiB | fits | 8.4–16.8 estimated tokens/s |
| Mac mini M6 (12-core GPU) 32GB | 24.0 GiB | 8.76 GiB | fits | 8.4–16.8 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB | 18.0 GiB | 8.76 GiB | fits | 15.2–30.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB | 36.0 GiB | 8.76 GiB | fits | 15.2–30.3 estimated tokens/s |
| Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB | 48.0 GiB | 8.76 GiB | fits | 15.2–30.3 estimated tokens/s |
| Mac Studio M5 Max (32-core GPU) 36GB | 27.0 GiB | 8.76 GiB | fits | 22.7–45.4 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 64GB | 48.0 GiB | 8.76 GiB | fits | 30.3–60.7 estimated tokens/s |
| Mac Studio M5 Max (40-core GPU) 128GB | 96.0 GiB | 8.76 GiB | fits | 30.3–60.7 estimated tokens/s |
| Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB | 72.0 GiB | 8.76 GiB | fits | 59.3–118.5 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB | 192.0 GiB | 8.76 GiB | fits | 59.3–118.5 estimated tokens/s |
| Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB | 384.0 GiB | 8.76 GiB | fits | 59.3–118.5 estimated tokens/s |
| MacBook Pro 14-inch M5 (10-core GPU) 24GB | 18.0 GiB | 8.76 GiB | fits | 7.6–15.1 estimated tokens/s |
| MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB | 36.0 GiB | 8.76 GiB | fits | 15.2–30.3 estimated tokens/s |
| MacBook Pro 16-inch M5 Max (40-core GPU) 128GB | 96.0 GiB | 8.76 GiB | fits | 30.3–60.7 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 16GB | 12.0 GiB | 8.76 GiB | fits | 5.9–11.9 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 24GB | 18.0 GiB | 8.76 GiB | fits | 5.9–11.9 estimated tokens/s |
| Mac mini (2024) M4 (10-core GPU) 32GB | 24.0 GiB | 8.76 GiB | fits | 5.9–11.9 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 24GB | 18.0 GiB | 8.76 GiB | fits | 13.5–27.0 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 48GB | 36.0 GiB | 8.76 GiB | fits | 13.5–27.0 estimated tokens/s |
| Mac mini (2024) M4 Pro (16-core GPU) 64GB | 48.0 GiB | 8.76 GiB | fits | 13.5–27.0 estimated tokens/s |
| Mac Studio (2025) M4 Max (32-core GPU) 36GB | 27.0 GiB | 8.76 GiB | fits | 20.3–40.5 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 64GB | 48.0 GiB | 8.76 GiB | fits | 27.0–53.9 estimated tokens/s |
| Mac Studio (2025) M4 Max (40-core GPU) 128GB | 96.0 GiB | 8.76 GiB | fits | 27.0–53.9 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB | 72.0 GiB | 8.76 GiB | fits | 40.5–80.9 estimated tokens/s |
| Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB | 192.0 GiB | 8.76 GiB | fits | 40.5–80.9 estimated tokens/s |
| NVIDIA GeForce RTX 3060 12GB | 10.8 GiB | 8.76 GiB | fits | 17.8–35.6 estimated tokens/s |
| NVIDIA GeForce RTX 3090 24GB | 21.6 GiB | 8.76 GiB | fits | 46.2–92.5 estimated tokens/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 14.4 GiB | 8.76 GiB | fits | 14.2–28.4 estimated tokens/s |
| NVIDIA GeForce RTX 4070 12GB GDDR6X | 10.8 GiB | 8.76 GiB | fits | 24.9–49.8 estimated tokens/s |
| NVIDIA GeForce RTX 4080 16GB | 14.4 GiB | 8.76 GiB | fits | 35.4–70.8 estimated tokens/s |
| NVIDIA GeForce RTX 4090 24GB | 21.6 GiB | 8.76 GiB | fits | 49.8–99.6 estimated tokens/s |
| NVIDIA GeForce RTX 5060 Ti 16GB | 14.4 GiB | 8.76 GiB | fits | 22.1–44.3 estimated tokens/s |
| NVIDIA GeForce RTX 5070 12GB | 10.8 GiB | 8.76 GiB | fits | 33.2–66.4 estimated tokens/s |
| NVIDIA GeForce RTX 5070 Ti 16GB | 14.4 GiB | 8.76 GiB | fits | 44.3–88.5 estimated tokens/s |
| NVIDIA GeForce RTX 5080 16GB | 14.4 GiB | 8.76 GiB | fits | 47.4–94.8 estimated tokens/s |
| NVIDIA GeForce RTX 5090 32GB | 28.8 GiB | 8.76 GiB | fits | 88.5–177.0 estimated tokens/s |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | 86.4 GiB | 8.76 GiB | fits | 88.5–177.0 estimated tokens/s |
| NVIDIA RTX 6000 Ada Generation 48GB | 43.2 GiB | 8.76 GiB | fits | 47.4–94.8 estimated tokens/s |
| Intel Arc B580 12GB | 10.8 GiB | 8.76 GiB | fits | 22.5–45.0 estimated tokens/s |
| AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB | 89.6 GiB | 8.76 GiB | fits | 12.6–25.3 estimated tokens/s |
| NVIDIA DGX Spark 128GB / 4TB | 96.0 GiB | 8.76 GiB | fits | 13.5–27.0 estimated tokens/s |
| 2 × GeForce RTX 3090 24GB (conditional 48GB aggregate) | 40.8 GiB | 8.76 GiB | Needs verification | Estimated speed unavailable |
| 2 × GeForce RTX 5090 32GB (conditional 64GB aggregate) | 54.4 GiB | 8.76 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 (qwen2); 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.