keyvan-ai/Mankei-1B-Chat-GGUF overview
<p align="center" <img src="mankei logo.png" width="200" alt="Mankei" </p Mankei 1B Chat — GGUF GGUF Quantisierungen von keyvan ai/Mankei 1B Chat https://huggi…
Runs locally from ~511.9 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Mankei-1B-Chat-f16.gguf | GGUF | F16 | 1.89 GB | Download |
| Mankei-1B-Chat-q3_k_m.gguf | GGUF | Q3_K_M | 511.9 MB | Download |
| Mankei-1B-Chat-q4_k_m.gguf | GGUF | Q4_K_M | 636.5 MB | Download |
| Mankei-1B-Chat-q5_k_m.gguf | GGUF | Q5_K_M | 727.1 MB | Download |
| Mankei-1B-Chat-q6_k.gguf | GGUF | Q6_K | 853.6 MB | Download |
| Mankei-1B-Chat-q8_0.gguf | GGUF | Q8_0 | 1.00 GB | Download |
Model Details
| Model ID | keyvan-ai/Mankei-1B-Chat-GGUF |
|---|---|
| Author | keyvan-ai |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | keyvan-ai/Mankei-1B-Chat |
| Last modified | 2026-08-12T10:34:25.000Z |
Model README
---
base_model: keyvan-ai/Mankei-1B-Chat
base_model_relation: quantized
license: apache-2.0
language:
- de
- en
pipeline_tag: text-generation
tags:
- gguf
- llama
- german
- deutsch
- cpu
- ollama
- llama.cpp
---
<p align="center"><img src="mankei-logo.png" width="200" alt="Mankei"></p>
Mankei-1B-Chat — GGUF
GGUF-Quantisierungen von keyvan-ai/Mankei-1B-Chat für llama.cpp und Ollama — läuft auf der CPU.
| Quantisierung | Größe | Download |
|---|---|---|
| f16 | 1,9 GB | Mankei-1B-Chat-f16.gguf |
| Q8_0 | 1,0 GB | Mankei-1B-Chat-q8_0.gguf |
| Q6_K | 854 MB | Mankei-1B-Chat-q6_k.gguf |
| Q5_K_M | 727 MB | Mankei-1B-Chat-q5_k_m.gguf |
| Q4_K_M | 637 MB | Mankei-1B-Chat-q4_k_m.gguf |
| Q3_K_M | 512 MB | Mankei-1B-Chat-q3_k_m.gguf |
# Ollama
ollama run hf.co/keyvan-ai/Mankei-1B-Chat-GGUF:Q4_K_M
# llama.cpp
llama-cli -hf keyvan-ai/Mankei-1B-Chat-GGUF:Q4_K_MEmpfohlenes Sampling: temperature 0.7 · top_p 0.9 · repetition_penalty 1.15.
Run keyvan-ai/Mankei-1B-Chat-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models