autotrust/GLM5.3-Flash-E224-DGX-Spark

image-text-to-text model by autotrust

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

[](https://news.guru.so/ui) autotrust/GLM5.3-Flash-E224-DGX-Spark is a compact build of zai-org/GLM-5.3-Flash for desktop Blackwell systems like NVIDIA DGX Spark. It's an unofficial derivative. It keeps 224 of the 288 routed experts in each layer by Neural Architecture Search (NAS), uses NVFP4 for the experts and still activates 18 B parameters per token. The weights take 141 GiB, which is small enough for two DGX Sparks connected by ConnectX-7 (256 GB of unified memory in total) with room left for long-context KV cache. A single 180 GB Blackwell GPU (B200/GB200) can also run it. The original GLM-5.3-Flash MTP layer ships unmodified in mtp/ (BF16) as an optional speculative-decoding draft. It gives about 1.85× single-stream decode speed on B200 at the same output quality. A ready-to-use NVFP4 export of the same draft ships in mtp-nvfp4/ (6.95 GB), the recommended draft on DGX Spark. The model keeps the full 154,880-token vocabulary and has the vision tower…

autotrust/GLM5.3-Flash-E224-DGX-Spark on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-17T12:24:11.713Z

Inside the original model card — Document outline
  1. GLM5.3-Flash-E224-DGX-Spark
  2. 🔴 Live: AutoTrust/GuruSearch recommendation & search demo → news.guru.so
  3. Designed for DGX Spark
  4. Benchmarks
  5. Headline
  6. Reasoning: the thinking budget matters
  7. Tool use: BFCL v4 (function calling, AST match)
  8. Throughput (single B200, reference only)
  9. MTP speculative decoding (optional)
  10. Where it loses vs. the 288-expert model
  11. Deployment
  12. Requirements

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

autotrust/GLM5.3-Flash-E224-DGX-Spark is a image-text-to-text model repository published by autotrust on Hugging Face. The source reports the vllm library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
image-text-to-text
Library
vllm
Recent downloads (30 days)
5,422
Cumulative likes
499
Hugging Face trending score
458
Reported safetensors parameters
127,627,162,814
Architecture
Glm5NextForConditionalGeneration
License
mit
Access
Not gated by Hugging Face
Created
2026-10-06T22:49:26.000Z
Last modified
2026-10-08T14:49:01.000Z

Compatibility and lineage

Reported languages: en, zh

Reported base models: zai-org/GLM-5.3-Flash

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.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-10-09T06:39:48.873Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

microsoft/Florence-2-base

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Qwen/Qwen3.8-27B-FP8

zai-org/GLM-5.3-Flash

Qwen/Qwen3.8-27B

Qwen/Qwen3.5-9B