flywheel-ai / text-generation updated 1 month ago

automotive

An open-source vertical AI-employee model from Flywheel by OpSpot, fine-tuned (LoRA) from Qwen/Qwen3.6-35B-A3B (Apache-2.0) for the automotive domain.

Params
34.7 B
Context
Downloads 30d
219 K
Likes
0
Commercial use: allowed apache-2.0 Not gated GGUF · SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 43 days
▲ 104 K in the last 30 days (32.1%)
323 K167 K
Aug 10Aug 24Sep 7Sep 21

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model-q4_k_m.gguf Q4_K_M 21.2 GB 29.0 GB ❌ Won’t fit
model.safetensors bf16 69.3 GB 82.0 GB ❌ Won’t fit
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
~ · ollama · Q4_K_M
$ ollama run automotive

# pin the quantization explicitly
$ ollama run automotive-q4_k_m
est. VRAM 29.0 GBon RTX 4090 · 24 GBJSON API →

Specifications

Architecture
Qwen3_5MoeForConditionalGeneration
Parameters
34.7 B
Tensor type
BF16
Licence
apache-2.0
First seen on the Hub
2026-06-21
Base model
Qwen3.6-35B-A3B
Training datasets
undisclosed
Added to our catalog
2026-08-10

Family

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

Compare with any text-generation model