LLM EXPLORER 63,892 MODELS INDEXED

Veloxy Flash 15B by zveloxy

By zveloxy · 806 downloads
HF Repo ↗ Copy URL

Veloxy Flash 15B is an open-source language model by zveloxy. Features: 9b LLM, VRAM: 18.8GB, Context: 512K, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  Agent Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.5-9b   Code   Conversational   Cot   Cybersecurity   En   Endpoints compatible   Gguf   Java21   Loom   Model-index   Q2   Quantized   Qwen3 5   Qwen3 5 text   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Think   Tool-calling   Tr   Turkish   Veloxy   Zero-refusal
Model Card on HF 🤗: https://huggingface.co/zveloxy/Veloxy-Flash-15B 

Veloxy Flash 15B Parameters and Internals

LLM NameVeloxy Flash 15B
Repository 🤗https://huggingface.co/zveloxy/Veloxy-Flash-15B 
Base Model(s)  Qwen/Qwen3.5-9B   Qwen/Qwen3.5-9B
Model Size9b
Required VRAM18.8 GB
Updated2026-10-12
Maintainerzveloxy
Model Typeqwen3_5_text
Model Files  0.9 GB   4.9 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   3.9 GB: 4-of-4   17.9 GB   3.8 GB   4.6 GB   5.6 GB   6.5 GB   7.4 GB   9.5 GB
Supported Languagesen tr
GGUF QuantizationYes
Quantization Typegguf|q2|q4_k|q5_k
Model ArchitectureQwen3_5ForCausalLM
Licenseapache-2.0
Context Length524288
Model Max Length524288
Transformers Version5.19.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size248320
Errorsreplace

Best Alternatives to Veloxy Flash 15B

Best Alternatives
Context / RAM
Downloads
Likes
Nyx RP 9B Instruct 2608 V1256K / 18.4 GB31675
...wen3.5 9B Abliterated MLX 4bit256K / 5 GB106310
Qwen3.5 Text 9B Bnb 4bit256K / 7.6 GB11004
Tmax 9B MLX 8bit0K / 9.5 GB791
Tmax 9B MLX 4bit0K / 5 GB451
...thos 9B V2 Heretic Abliterated1024K / 17.9 GB803
Le Gros Chaton256K / 17.9 GB2351
NeoHorse 1 9B256K / 18 GB1250196
...yber Ornith 1.5 9B OBLITERATED256K / 17.9 GB14247
JEV 9B256K / 17.8 GB47112
Note: green Score (e.g. "73.2") means that the model is better than zveloxy/Veloxy-Flash-15B.