4.9 KiB
4.9 KiB
license, language, library_name, pipeline_tag, base_model, base_model_relation, tags
| license | language | library_name | pipeline_tag | base_model | base_model_relation | tags | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| apache-2.0 |
|
gguf | text-generation | fableforge-ai/FableForge-1.5B | quantized |
|
FableForge-1.5B-GGUF
FableForge generalist — all NEXUS domains distilled into one model.
Base model: fableforge-ai/FableForge-1.5B · Part of the FableForge ecosystem.
⚡ Quickest start — Ollama (these pulls credit the source, not a mirror)
ollama run hf.co/fableforge-ai/FableForge-1.5B-GGUF:Q4_K_M
🦙 llama.cpp
llama-cli -hf fableforge-ai/FableForge-1.5B-GGUF:Q4_K_M -p "Hello!"
💠 LM Studio
Search fableforge-ai/FableForge-1.5B-GGUF and pick a quant below.
📦 Provided quants (download one file, not the whole repo)
| File | Quant | Size | Notes |
|---|---|---|---|
| FableForge-1.5B-F16.gguf | F16 |
3.09 GB | Full precision (unquantized). Reference / conversion. |
| FableForge-1.5B-Q8_0.gguf | Q8_0 |
1.65 GB | Extremely high quality — usually overkill. |
| FableForge-1.5B-Q6_K.gguf | Q6_K |
1.33 GB | Very high quality, near-perfect. Recommended if you have the RAM. |
| FableForge-1.5B-Q5_K_M.gguf | Q5_K_M |
1.21 GB | High quality. Recommended. |
| FableForge-1.5B-Q4_K_M.gguf | Q4_K_M |
1.06 GB | ⭐ Best size/quality balance — default pick for most users. |
| FableForge-1.5B-IQ4_XS.gguf | IQ4_XS |
0.90 GB | imatrix — great quality, smaller than Q4_K_S. Recommended for low RAM. |
| FableForge-1.5B-Q4_0.gguf | Q4_0 |
0.99 GB | Legacy format — prefer Q4_K_M. |
| FableForge-1.5B-Q3_K_M.gguf | Q3_K_M |
0.91 GB | Lower quality; usable when RAM is tight. |
| FableForge-1.5B-IQ3_XXS.gguf | IQ3_XXS |
0.67 GB | imatrix very low quality. |
| FableForge-1.5B-Q2_K.gguf | Q2_K |
0.68 GB | Very low quality — surprisingly usable. |
| FableForge-1.5B-IQ2_XXS.gguf | IQ2_XXS |
0.51 GB | Tiny imatrix — last resort. |
| FableForge-1.5B-IQ1_S.gguf | ? |
0.44 GB | |
| FableForge-1.5B-imatrix.gguf | ? |
0.00 GB |
Not sure? Take Q4_K_M. Low RAM → IQ4_XS. Max quality → Q6_K.
🧠 Prompt format (ChatML)
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
🌌 See it live — the FableForge demos
This family powers a galaxy of free, interactive HF Spaces:
🔗 Related models
- 🧠 Base model (safetensors):
FableForge-1.5B - 🔄 V2 GGUF:
FableForge-1.5B-v2-GGUF
⭐ Like & share — it helps people find the source instead of a mirror.