kindlingai/glm-5.3-exlr8-k2-k3-k4
text-generation model by kindlingai
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Version 0.5 (git tag v0.5). See the changelog. Weight set ID: 2011c0cedde962d19fc43e74c1d409279e398d40d27a6fdb4bcb7b49ea2ea6fb (see Identifying the weights). Also mirrored on ModelScope: kindlingai/glm-5.3-exlr8-k2-k3-k4. A quantization of GLM-5.3 (744B MoE: 256 routed experts × 75 MoE layers plus the MTP layer 78, dense layers 0-2) in the exlr8 v2 format, built for NVIDIA GB10-class unified-memory devices served at tensor-parallel sizes 3-7 (TP=4, 5 and 6 are the main targets; see "Known results so far" for what has been tested). KindlingAI: It fetches each box's part of this repository and serves it at TP=3 and 4. a loader or kernel against known-good weights. Other engines: EXLR8 is a new quantization format. It reuses EXL3's trellis encoding — QTIP-style codes where each 16×16 tile is a path through a 16-bit-state trellis, every weight contributing K new bits, found by Viterbi search over the mcg codebook — but re-engineers everything around it for MoE models served…
Read the full model card ↗ · Preview checked 2026-10-27T23:37:51.361Z
Inside the original model card — Document outline
- GLM-5.3 · exlr8 (K2/K3/K4)
- Engine support
- How does this differ from other quantization formats?
- Why three widths?
- What is in this repository
- Manifests
- Width profiles
- Identifying the weights
- Index slices
- Loader
- Calibration
- Loading
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
kindlingai/glm-5.3-exlr8-k2-k3-k4 is a text-generation model repository published by kindlingai on Hugging Face. The source reports the trellis library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- trellis
- Recent downloads (30 days)
- 1,113,219
- Cumulative likes
- 26
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- GlmMoeDsaForCausalLM
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-08T03:20:20.000Z
- Last modified
- 2026-10-26T18:00:53.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: zai-org/GLM-5.3-BF16
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:51:29.042Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.