ibm-granite/granite-4.2-8b-GGUF
published by IBMhuggingface.co/ibm-granite/granite-4.2-8b-GGUF
This is a quantization of Granite 4.2 8B, not an independent model. Parameters, benchmarks, prices and lineage are recorded on the canonical model. Open Granite 4.2 8B →
Updated 5 h ago · first seen 11 Sept 2026
model_01M294YP6NHHDZ7ZQPM8ZDH8N0
- File size
- —
- Format
- Downloads
- Published
Artifact facts
- Quantization format
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium
- Downloads
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 h agomedium
- Likes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 h agomedium
- Hugging Face repo
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium
- Base model
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium
- Library name
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium
- Gated
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium
- License
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium
- Release date
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium
- Last modified
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium
- Tags
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium
Hardware fit (this packaging)
Assumptions (7)
- Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
- bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
- KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
- A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
- Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
- Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
- Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.
Timeline
ibm-granite/granite-4.2-8b-GGUF: parameter count changed from 8000000000 to 8791592960
Parameters8B→8.79Bhuggingfaceibm-granite/granite-4.2-8b-GGUF: parameter count changed from 8791592960 to 8000000000
Parameters8.79B→8Bhuggingface
Provenance
Attributed facts
21
Source tiers
T221
Freshest observation
5 h ago
Conflicts
None
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.