---

license: apache-2.0

base_model:

• ibm-granite/granite-4.2-8b

base_model_relation: quantized

library_name: gguf

pipeline_tag: text-generation

tags:

• wekala
• gguf

---

granite-4.2-8b-gguf

Consumer-supplied Wekala model-library assets derived from the attributed official publisher. Models and this repository are distributed separately from the Wekala SDK.

Origin and licence

| Field | Value |

| --- | --- |

| Original developer | IBM |

| Original model | ibm-granite/granite-4.2-8b |

| Pinned source revision | f8de16cdcdbc6c779ca517604e050d82cc119e44 |

| Original publication | 2026-08-25 (day) |

| Date evidence | Publisher source |

| Licence | apache-2.0; preserved in LICENSE |

| Full source parameters | 8,791,592,960 (includes embeddings and source modalities) |

| Nile Academy role | Official artifact mirror or explicitly recorded format conversion; no additional training |

Original publisher cards and available notices are preserved in provenance/. The original model licence governs the weights; this repository grants no rights to the Wekala SDK.

Files and quantization

Q8_0 is the higher-precision comparison; Q6_K/Q5_K_M trade memory for precision; Q4_K_M needs paired task evaluation. No general quality-loss or 8GB-fit qualification yet.

| File | Quantization | Size (GB) | Origin |

| --- | --- | ---: | --- |

| granite-4.2-8b-Q4_K_M.gguf | Q4_K_M | 5.348 | official publisher export |

| granite-4.2-8b-Q5_K_M.gguf | Q5_K_M | 6.254 | official publisher export |

| granite-4.2-8b-Q6_K.gguf | Q6_K | 7.216 | official publisher export |

| granite-4.2-8b-Q8_0.gguf | Q8_0 | 9.346 | official publisher export |

Exact file SHA-256 values, upstream paths/revisions and conversion receipts are recorded in model-metadata.json.

Published benchmarks

Publisher-reported source-model scores follow. They are not Wekala measurements of these quantized files. Harness, precision, reasoning settings and task versions differ; do not treat them as a normalized cross-model ranking.

| Benchmark | Score (%) | Mode / settings |

| --- | ---: | --- |

| BFCLv4 | 52.39 | publisher-default; Publisher source protocol; not normalized across models or measured on this quantization. |

| MMLU-Pro | 74.04 | publisher-default; Publisher source protocol; not normalized across models or measured on this quantization. |

| GPQA (subset unspecified) | 64.14 | publisher-default; Publisher source protocol; not normalized across models or measured on this quantization. |

| AIME25 | 86.67 | publisher-default; Publisher source protocol; not normalized across models or measured on this quantization. |

| LiveCodeBench v6 | 73.24 | publisher-default; Publisher source protocol; not normalized across models or measured on this quantization. |

Exact source card.

Qualification and use

Downloadable declarative asset. Wekala native chat/tool/template, sustained GPU fit and mobile/browser qualification are pending; no automatic backend installation.

Wekala broad quantization-quality qualification: not qualified. No general “no significant quality loss” claim is made. Official QAT or publisher comparisons are attributed separately. Before recommendation, use paired reference/variant evaluation across instruction, knowledge, math, multilingual/Arabic and tool tasks under the registered Wekala campaign.

Device fit is separate: weight size excludes context state, scratch buffers and driver headroom. CPU and CUDA are execution backends for the same weight file, not separate models. Mobile/browser and sustained 8GB-VRAM operation require their own measured profiles.

Models can produce incorrect or unsafe outputs. Tool calls are proposals subject to the consuming application’s permissions and controller admission.