Scantist/GLM-5.3-SLIM-GGUF
text-generation model by Scantist
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.
A GLM-5.3-class model that runs on a single NVIDIA B200, or on a Mac Studio with 192 GB or more of unified memory (with mlx-serve). At 179.9 GB it is 24.6% smaller than the 256-expert UD-IQ2M (238.6 GB), which does not fit in the memory of one B200 or a 192 GB Mac. On one B200 the whole model sits on the GPU and about 100K tokens of KV cache are left for up to 10 parallel requests; in our tests it scores 92.7% on HumanEval. GLM-5.3 with a 192-expert MoE architecture found by neural architecture search (NAS): every MoE layer keeps 192 of the original 256 routed experts. The model is built from Unsloth's UD-IQ2M GGUF quantization. behind GLM-5.3-SLIM-E192. Each MoE layer (3-77) keeps the experts chosen by the search; the other 64 routed experts per layer are removed. and expprobsb, so each expert is one contiguous byte range.…
Read the full model card ↗ · Preview checked 2026-11-08T09:43:33.379Z
Inside the original model card — Document outline
- GLM-5.3-SLIM-GGUF (E192, UD-IQ2M)
- How it was made
- Files
- Deploying on a single NVIDIA B200
- 1. Requirements
- 2. Build llama.cpp with CUDA
- 3. Download
- 4. Memory budget
- 5. Start the server
- 6. Choosing -c and -np
- 7. Run GPQA-Diamond
- 8. Notes
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
Scantist/GLM-5.3-SLIM-GGUF is a text-generation model repository published by Scantist on Hugging Face. A library was not reported.
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
- Not reported
- Recent downloads (30 days)
- 208
- Cumulative likes
- 795
- Hugging Face trending score
- 99
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-11-02T13:11:14.000Z
- Last modified
- 2026-11-03T01:48:48.000Z
Compatibility and lineage
Reported languages: en, zh
Reported base models: zai-org/GLM-5.3
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 2026-11-08T06:53:26.831Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.