andynoodles/Edge0-145B-NVFP4-vLLM

text-generation model by andynoodles

Open original source ↗

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.

Edge0/Edge0-145B-NVFP4 (revision cf4c3d9), converted to safetensors for edge0-vllm, a vLLM plugin that serves it on one RTX 5090 32 GB. Same weights, no retraining. An independent conversion by Andy Chen (andynoodles), not made or endorsed by Edge0, Qwen, vLLM or Strata. It needs the plugin. Stock vLLM and transformers cannot load this checkpoint. acceptance, never the output. MTP draft vocabulary as JSON). the upstream repository. Every change: CHANGES.md. Tested on one box: RTX 5090 32 GB, Ryzen 9 9950X, 60 GiB DDR5, NGC nvcr.io/nvidia/vllm:26.11-py3 (vLLM 0.33). memlock must be unlimited. decode step. If it must live on another drive, leave a symlink named ple-fp8.gguf in the folder. For the faster single-request preset (PRESET=single), see the plugin README. It also needs the DFlash2 drafter (Apache-2.0), downloaded separately. () and 248044 (). One RTX 5090, ShareGPT prompts, thinking off, temperature 0. The single-request rows stop at EOS for both…

andynoodles/Edge0-145B-NVFP4-vLLM on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-21T07:19:39.775Z

Inside the original model card — Document outline
  1. Edge0-145B-NVFP4-vLLM
  2. Changes from upstream
  3. Requirements
  4. Quick start
  5. Performance
  6. License

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

andynoodles/Edge0-145B-NVFP4-vLLM is a text-generation model repository published by andynoodles 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
text-generation
Library
vllm
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
57,764,125,312
Architecture
Edge0ForCausalLM
License
other
Access
Not gated by Hugging Face
Created
2026-11-21T06:13:16.000Z
Last modified
2026-11-21T06:37:38.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: Edge0/Edge0-145B-NVFP4

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 2026-11-21T07:02:33.996Z. 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

openai-community/gpt2

Qwen/Qwen3-0.6B

Qwen/Qwen3-14B

deepseek-ai/DeepSeek-V3.2

Qwen/Qwen2.5-7B-Instruct

Qwen/Qwen3-8B