autotrust / image-text-to-text Open weights updated 1 week ago

JEV-27B-VL

Name: JEV-27B-VL
Author: autotrust

> [!IMPORTANT] > Try AutoTrust/GuruSearch live (new, 11 October 2026). A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > Recommendation: the latest headlines from 6 news feeds, ranked by importance. > Search: results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a shor...

Params

27.8 B

Context

—

Downloads 30d

2.2 M

Likes

1,137

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 19 days

2.2 M1.3 M

Oct 6Oct 12Oct 18Oct 24

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	56.0 GB	66.3 GB	❌ Won’t fit

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

Specifications

Architecture: Qwen3_5ForConditionalGeneration
Parameters: 27.8 B
Tensor type: BF16
Licence: apache-2.0
First seen on the Hub: 2026-09-30
Base model: Qwen3.8-27B
Training datasets: SargeDev/jev-distill-corpus-v3
Added to our catalog: 2026-10-06

Family

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

Base Qwen3.8-27B Qwen 7.7 M

Compare with any image-text-to-text model

Popular comparisons

gemma-4-26B-A4B-it 9.1 M gemma-4-31B-it 8.5 M Qwen3.8-27B 7.7 M Qwen3.8-27B-FP8 4.3 M Qwen3.6-35B-A3B 3.7 M Qwen3.6-35B-A3B-FP8 3.5 M

Appears in

Fastest-growing VLMs