---

language:

• hu

license: mit

tags:

• hungarian
• causal-lm
• llama
• gguf
• llama-cpp
• sentencepiece

pipeline_tag: text-generation

model-index:

• name: csermely-gguf

results: []

---

Csermely (GGUF)

GGUF quantized versions of Csermely — a 190M parameter Hungarian language model. Part of the Emese model family.

Compatible with llama.cpp, Ollama, LM Studio, and other GGUF-compatible runtimes.

For the full-precision HuggingFace version, see emese-tech/csermely.

Available Quantizations

| File | Quantization | Size | Description |

|------|-------------|------|-------------|

| csermely-f16.gguf | F16 | 418 MB | Full float16, reference quality |

| csermely-q8_0.gguf | Q8_0 | 223 MB | 8-bit, near-lossless quality |

| csermely-q4_k_m.gguf | Q4_K_M | 157 MB | 4-bit, good quality/size balance |

Usage

llama.cpp

./llama-cli -m csermely-q8_0.gguf -p "A magyar nyelv" -n 100 --repeat-penalty 1.2 --chat-template none

Ollama

ollama run emese-tech/csermely-gguf

Model Details

| | |

|---|---|

| Version | 0.2 |

| Parameters | 190.2M |

| Architecture | LLaMA-style (decoder-only transformer) |

| Context length | 4,096 tokens (YaRN RoPE, 4× factor) |

| Vocabulary | 32,000 (SentencePiece Unigram, Hungarian) |

| License | MIT |