JEV-27B
> [!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
26.9 B
Context
262,144
Downloads 30d
340 K
Likes
85
Download history
tracking started — chart appears after 7 days of snapshots (6 recorded)340 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 | 54.7 GB | 64.7 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 54.7 GB | 189.7 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_5ForCausalLM
- Parameters
- 26.9 B
- Tensor type
- BF16
- Context length
- 262,144
- Vocabulary
- 248,320
- Layers / heads
- 64 / 24
- Licence
- apache-2.0
- First seen on the Hub
- 2026-09-25
- Base model
- Qwen3.8-27B
- Training datasets
- SargeDev/jev-distill-corpus-v3
- HumanEval (reported)
- 0.78
- jev-distill-corpus-v3 · test_set_30k (reported)
- 0.958
- Added to our catalog
- 2026-10-19
Compare with any text-classification model