LLM EXPLORER 63,069 MODELS INDEXED

Clef Flash FP8 by prithivMLmods

By prithivMLmods · 109 downloads
HF Repo ↗ Copy URL

Clef Flash FP8 is an open-source language model by prithivMLmods. Features: 9.4b LLM, VRAM: 13.6GB, License: apache-2.0, LLM Explorer Score: 0.3.

Base model:cloudflare/clef-fla... Base model:quantized:cloudflar...   Classification   Clef   Cloudflare   Compressed-tensors   Conversational   Custom-code   En   Endpoints compatible   Fp8   Image-text-to-text   Image-text-to-typed-output   Llm-compressor   Multimodal   Post-train   Qwen3.5   Qwen3 5   Region:us   Safetensors   Sharded   Structured-output   Systemone   Tensorflow   Vllm   W8a8
Model Card on HF 🤗: https://huggingface.co/prithivMLmods/clef-flash-FP8 

Clef Flash FP8 Parameters and Internals

LLM NameClef Flash FP8
Repository 🤗https://huggingface.co/prithivMLmods/clef-flash-FP8 
Base Model(s)  Cloudflare/clef-flash   Cloudflare/clef-flash
Model Size9.4b
Required VRAM13.6 GB
Updated2026-10-05
MaintainerprithivMLmods
Model Typeqwen3_5
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   3.6 GB: 3-of-3
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.10.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Clef Flash FP8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen Image 2.1 PE I2I0K / 3.6 GB550142
Qwen Image 2.1 PE T2I0K / 3.6 GB188543
Qwen Image 2.1 PE T2I MLX0K / 18.8 GB7291
Qwen Image 2.1 PE I2I MLX0K / 18.8 GB6431
Qwen Image 2.1 PE I2I Heretic0K / 18.8 GB1621
Qwen Image 2.1 PE I2I FP80K / 13.5 GB1122
Qwen Image 2.1 PE T2I FP80K / 13.5 GB1361
Qwen Image 2.1 PE I2I Heretic0K / 18.8 GB781
Qwen Image 2.1 PE T2I Heretic0K / 18.8 GB700
Qwen3.5FundusReasoner Base0K / 18.8 GB91
Note: green Score (e.g. "73.2") means that the model is better than prithivMLmods/clef-flash-FP8.