Dennis1315/cypher-math-prm-8b-lora-gguf overview
Cypher MATH PRM 8B — LoRA GGUF runtime, sin merge Adaptador LoRA del especialista destilado MATH PRM 8B del ecosistema Cypher, convertido a formato GGUF para s…
Runs locally from ~83.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| MATH-PRM-8B-lora.gguf | GGUF | GGUF | 83.3 MB | Download |
Model Details
| Model ID | Dennis1315/cypher-math-prm-8b-lora-gguf |
|---|---|
| Author | Dennis1315 |
| Pipeline | — |
| License | apache-2.0 |
| Base model | Qwen/Qwen3-8B |
| Last modified | 2026-09-15T06:29:11.000Z |
Model README
---
license: apache-2.0
tags:
- cypher
- lora
- gguf
- distilled
base_model: Qwen/Qwen3-8B
---
Cypher MATH-PRM-8B — LoRA GGUF (runtime, sin merge)
Adaptador LoRA del especialista destilado MATH-PRM-8B del ecosistema Cypher,
convertido a formato GGUF para servir EN RUNTIME con llama.cpp:
llama-server --model Qwen3-8B-Q4_K_M.gguf --lora MATH-PRM-8B-lora.gguf
No requiere merge con la base: se aplica al vuelo. Origen: adapter F32 del
repo cypher-MATH-PRM-8B-v8-GGUF (r=16, alpha=32, 7 target_modules).
Run Dennis1315/cypher-math-prm-8b-lora-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models