JEV-9B
> [!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
9.0 B
Context
262,144
Downloads 30d
564 K
Likes
94
Download history
daily snapshots · 19 days564 K306 K
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 | 18.4 GB | 22.1 GB | ⚠️ Tight — reduce context |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 18.4 GB | 63.7 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
- 9.0 B
- Tensor type
- BF16
- Context length
- 262,144
- Vocabulary
- 248,320
- Layers / heads
- 32 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-09-23
- Base model
- Qwen3.5-9B
- Training datasets
- SargeDev/jev-distill-corpus-v3
- HumanEval (reported)
- 0.707
- jev-distill-corpus-v3 · test_set_30k (reported)
- 0.954
- Added to our catalog
- 2026-10-06
Compare with any text-classification model