cevher-406m — GGUF

SmolLM2 (Llama) mimarisiyle sıfırdan eğitilmiş modelin GGUF sürümleri.

Eğitim token sayısı: 3.525 B · hidden 1024 · 34 katman.

| Dosya | Boyut |

|---|---|

| cevher-406m-BF16.gguf | 778 MB |

| cevher-406m-Q8_0.gguf | 414 MB |

| cevher-406m-Q5_K_M.gguf | 281 MB |

| cevher-406m-Q4_K_M.gguf | 245 MB |

llama.cpp

llama-cli -m cevher-406m-Q4_K_M.gguf -p "Merhaba" -cnv

ollama create cevher-406m -f Modelfile
ollama run cevher-406m

Dosyayı ~/.cache/lm-studio/models/bcckfdn/cevher-test-2-GGUF/ altına koyun ya da uygulama içinden arayın.

Question 2

What license applies to bcckfdn/cevher-test-2-GGUF?

Accepted Answer

License: apache-2.0. Verify terms on Hugging Face before commercial use.

Question 3

How do I run bcckfdn/cevher-test-2-GGUF locally?

Accepted Answer

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Question 4

How much VRAM or disk space does bcckfdn/cevher-test-2-GGUF need?

Accepted Answer

Runs locally from ~244.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

File	Type	Quantization	Size	Link
cevher-406m-BF16.gguf	GGUF	BF16	778.0 MB	Download
cevher-406m-Q4_K_M.gguf	GGUF	Q4_K_M	244.7 MB	Download
cevher-406m-Q5_K_M.gguf	GGUF	Q5_K_M	281.3 MB	Download
cevher-406m-Q8_0.gguf	GGUF	Q8_0	414.3 MB	Download