What are the hardware requirements for Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE?

Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE requires approximately 1.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE and how large is it?

Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE is developed by d0xin, a model with 119.6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE?

Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE by d0xin — VRAM 1.6GB

Name: Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE
Author: d0xin

Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE is an open-source language model by d0xin. Features: 119.6b LLM, VRAM: 1.6GB, LLM Explorer Score: 0.3.

8-bit Base model:quantized:ukisai/sw... Base model:ukisai/swift-1.5-qw... Blackwell Flash-next Fp8 Local-llm Modelopt Nvfp4 Pennyroyal Qwen Qwen3.8 Qwen4 exp Region:us Safetensors Sglang Swift

Model Card on HF 🤗: https://huggingface.co/d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE

Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE Parameters and Internals

LLM Name	Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE
Repository 🤗	https://huggingface.co/d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE
Base Model(s)	ukisai/Swift-1.5-Qwen3.8-Flash-Next-NVFP4 ukisai/Swift-1.5-Qwen3.8-Flash-Next-NVFP4
Model Size	119.6b
Required VRAM	1.6 GB
Updated	2026-10-05
Maintainer	d0xin
Model Type	qwen4_exp
Model Files	1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB 1.6 GB
Model Architecture	Qwen4ExpForConditionalGeneration
Transformers Version	5.8.0.dev0

Rank the Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Swift 1.5 Qwen3.8 Flash Next NVFP4 FP8PLE

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 Flash Next NVFP4	0K / 78.9 GB	13321	114
Qwen3.8 Flash Next NVFP4	0K / 0.4 GB	2297	40
Qwen3.8 Flash Next NVFP4	0K / 1.4 GB	7533	10
...8 Flash Next ABLITERATED NVFP4	0K / 0.4 GB	1434	12
...Flash Next CYBERSECURITY NVFP4	0K / 0.4 GB	996	6
...3.8 Flash Next Mixed NVFP4 FP8	0K / 0.1 GB	815	8
Qwen3.8 Flash Next NVFP4 FP8	0K / 0.4 GB	316	4
...xt RadixArk NVFP4 Hybrid Sharp	0K / 0.4 GB	329	1
...n3.8 Flash Next DERISKED NVFP4	0K / 0.4 GB	236	3
...ash Next NVFP4 Reshard Mtp Fix	0K / 1.1 GB	116	3

Note: green Score (e.g. "73.2") means that the model is better than d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE.