AvitoTech / text-generation updated 8 months ago

avibe

Name: avibe
Author: AvitoTech

A-vibe это большая языковая модель, созданная Авито Тех, дочерней технологической компанией Авито, на базе открытой модели Qwen3-8B-Base. Мы адаптировали Qwen3-8B-Base под русский язык и домен Авито с помощью нескольких шагов: 1. Сделали свой токенизатор, оптимальный для русского и английского языка 2. Подменили оригинальный токенизатор Qwen3-8B-Base на собственный токенизатор 3. Обучили полученную модель на большом...

Params

7.9 B

Context

32,768

Downloads 30d

173 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (5 recorded)

173 K downloads in the last 30 days

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	15.8 GB	19.1 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 32K ctx	15.8 GB	22.6 GB	⚠️ Tight — reduce context

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/avibe
{
  "hf_id": "AvitoTech/avibe",
  "params_b": 7.90,
  "context_length": 32768,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 173439,
  "vram_estimates": [
    { "quant": "bf16", "gb": 19.1 }
  ],
  "updated_at": "2026-08-02T01:00:31Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Qwen3ForCausalLM
Parameters: 7.9 B
Tensor type: BF16
Context length: 32,768
Vocabulary: 116,394
Layers / heads: 36 / 32
Licence: apache-2.0
First seen on the Hub: 2025-10-20
Base model: Qwen3-8B
Training datasets: undisclosed
Added to our catalog: 2026-08-02

Family

Base model and the most-downloaded derivatives in the catalog.

Base Qwen3-8B Qwen 16.3 M

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB