fehm-8b-v1-GGUF/README.md

license, language, base_model, tags, model_name, pipeline_tag

license	language	base_model	tags	model_name	pipeline_tag
apache-2.0	tr en	Qwen/Qwen3-8B	text-generation conversational turkish nage conflux gguf	Fehm-8B	text-generation

Fehm-8B GGUF — Nage AI

Fehm (Arabic: understanding, deep comprehension) is Nage AI's general assistant model. Fine-tuned from Qwen3-8B using CONFLUX cross-architecture knowledge transfer.

Downloads

File	Quant	Size	Use case
fehm-8b-v1-Q4_K_M.gguf	Q4_K_M	5.0 GB	Ollama, LM Studio, mobile
fehm-8b-v1-Q8_0.gguf	Q8_0	8.7 GB	High quality inference

Benchmarks

Benchmark	Score
MMLU (5-shot)	74.95%
HumanEval (pass@1)	71.34%
SFT val loss	0.671 (CONFLUX) vs 0.717 (baseline)

CONFLUX Framework

Trained with CONFLUX v0.3.0 — cross-architecture knowledge transfer (Llama-3.1-8B source).

• 6.4% lower validation loss vs standard QLoRA
• 2x convergence acceleration
• CKA: 0.817 | EVR: 0.9946

Training

• Base: Qwen3-8B (Apache 2.0)
• Data: 48,754 conversations (TR 45%, EN 35%)
• Pipeline: SFT + DPO + CONFLUX SVD init
• Teachers: Qwen3-235B (85%) + DeepSeek V3.2 (5%)

Nage Models

Model	Size	Role
Chi (Japanese)	8B	Gateway
Fehm (Arabic)	8B	Assistant
Ming (Chinese)	8B	Code
Cortex (Latin)	14B	Orchestrator
Bilge (Turkish)	14B	ML Expert

Links

• Nage AI
• CONFLUX
• FP16 Model

License

Apache 2.0