Home » org.modeljars » huggingface

Group: Modeljars HuggingFace
Sort by:Popular▼

1.Qwen3 0.6B GGUF Q4_01 usages

org.modeljars.huggingface » ggml-org.qwen3-0.6b-gguf.q4_0 Apache

Small Apache-2.0 Qwen3 text-generation fixture used by the pure-Java models backend integration tests.
Last Release on Aug 2, 2026

2.Granite 4.1 3b GGUF Q4_K_M1 usages

org.modeljars.huggingface » ibm-granite.granite-4.1-3b-gguf.q4_k_m Apache

Pinned local-inference GGUF artifact for granite-4.1-3b, verified by immutable revision, byte size, and SHA-256.
Last Release on Sep 17, 2026

3.Qwen3 1.7B GGUF Q8_01 usages

org.modeljars.huggingface » qwen.qwen3-1.7b-gguf.q8_0 Apache

Apache-2.0 Qwen3 model qualified for pure-Java chat and generative tool calling, including complete Spring AI and LangChain4j tool loops.
Last Release on Sep 4, 2026

4.DeepSeek R1 Distill Qwen 1.5B GGUF Q4_K_M

org.modeljars.huggingface » bartowski.deepseek-r1-distill-qwen-1.5b-gguf.q4_k_m MIT

Pinned local-inference GGUF artifact for DeepSeek-R1-Distill-Qwen-1.5B, verified by immutable revision, byte size, and SHA-256.
Last Release on Aug 2, 2026

5.Google Gemma 3 1b It GGUF Q4_K_M

org.modeljars.huggingface » bartowski.google-gemma-3-1b-it-gguf.q4_k_m

Pinned local-inference GGUF artifact for google gemma-3-1b-it, verified by immutable revision, byte size, and SHA-256.
Last Release on Aug 2, 2026

6.Granite Embedding 107m Multilingual GGUF Q4_K_M

org.modeljars.huggingface » bartowski.granite-embedding-107m-multilingual-gguf.q4_k_m Apache

Pinned GGUF embedding artifact for granite-embedding-107m-multilingual, verified by immutable revision, byte size, and SHA-256.
Last Release on Sep 2, 2026

7.Llama 3.2 1B Instruct GGUF Q4_K_M

org.modeljars.huggingface » bartowski.llama-3.2-1b-instruct-gguf.q4_k_m

Pinned local-inference GGUF artifact for Llama-3.2-1B-Instruct, verified by immutable revision, byte size, and SHA-256.
Last Release on Aug 2, 2026

8.Llama 3.2 3B Instruct GGUF Q4_K_M

org.modeljars.huggingface » bartowski.llama-3.2-3b-instruct-gguf.q4_k_m

Pinned local-inference GGUF artifact for Llama-3.2-3B-Instruct, verified by immutable revision, byte size, and SHA-256.
Last Release on Aug 2, 2026

9.Qwen2.5 Math 1.5B Instruct GGUF Q4_K_M

org.modeljars.huggingface » bartowski.qwen2.5-math-1.5b-instruct-gguf.q4_k_m Apache

Apache-2.0 Qwen2.5 math specialist for English and Chinese chain-of-thought and tool-integrated reasoning.
Last Release on Aug 2, 2026

10.Yi Coder 1.5B Chat GGUF Q4_K_M

org.modeljars.huggingface » bartowski.yi-coder-1.5b-chat-gguf.q4_k_m Apache

Apache-2.0 Yi-Coder 1.5B Chat imatrix GGUF artifact pinned by immutable revision, byte size, and SHA-256.
Last Release on Aug 5, 2026

11.Cactus Compute Needle 2 CACT CQ2 Mixed

org.modeljars.huggingface » cactus-compute.needle2-cact.cq2_mixed Apache

Compact 43.6M-parameter Needle 2 model for local tool selection, structured tool calls, argument extraction, and calibrated refusal.
Last Release on Sep 4, 2026

12.MS MARCO MiniLM L6 V2 Reranker Corrected Q4_K Imatrix

org.modeljars.huggingface » cstr.ms-marco-minilm-l-6-v2-gguf.q4_k_imatrix_g7c_f7 Apache

Compact BERT cross-encoder reranker qualified against ONNX logits and an independent implementation of the same quantized artifact.
Last Release on Sep 7, 2026

13.Meta MobileMoE S QAT INT4 G32

org.modeljars.huggingface » facebook.mobilemoe-s-qat.int4_g32

Meta's 1.26B-parameter, 272M-active on-device mixture-of-experts model, executed directly from its packed group-32 INT4 Safetensors checkpoint by the pure-Java Models backend.
Last Release on Sep 4, 2026

14.Embeddinggemma 300M GGUF Q8_0

org.modeljars.huggingface » ggml-org.embeddinggemma-300m-gguf.q8_0

Pinned GGUF embedding artifact for embeddinggemma-300M, verified by immutable revision, byte size, and SHA-256.
Last Release on Aug 11, 2026

15.Gemma 4 26B A4B It GGUF Q4_K_M

org.modeljars.huggingface » ggml-org.gemma-4-26b-a4b-it-gguf.q4_k_m Apache

Pinned local-inference GGUF artifact for gemma-4-26B-A4B-it, verified by immutable revision, byte size, and SHA-256.
Last Release on Aug 2, 2026

16.SmolLM3 3B GGUF Q4_K_M

org.modeljars.huggingface » ggml-org.smollm3-3b-gguf.q4_k_m Apache

Officially maintained Apache-2.0 SmolLM3 3B artifact for compact long-context reasoning and chat.
Last Release on Sep 4, 2026

17.Indian Legal Qwen2.5 3B GGUF Q4_K_M

org.modeljars.huggingface » gsms-b.indian-legal-qwen2.5-3b-gguf.q4_k_m Apache

Pinned local-inference GGUF artifact for Indian-Legal-Qwen2.5-3B, verified by immutable revision, byte size, and SHA-256.
Last Release on Aug 2, 2026

18.H2O Danube2 1.8B Chat GGUF Q4_K_M

org.modeljars.huggingface » h2oai.h2o-danube2-1.8b-chat-gguf.q4_k_m Apache

First-party H2O Danube2 1.8B Chat GGUF artifact pinned by immutable revision, byte size, and SHA-256.
Last Release on Aug 2, 2026

19.H2O Danube3 500M Chat GGUF Q4_K_M

org.modeljars.huggingface » h2oai.h2o-danube3-500m-chat-gguf.q4_k_m Apache

First-party H2O Danube3 500M Chat GGUF artifact pinned by immutable revision, byte size, and SHA-256.
Last Release on Aug 5, 2026

20.SmolLM2 1.7B Instruct GGUF Q4_K_M

org.modeljars.huggingface » huggingfacetb.smollm2-1.7b-instruct-gguf.q4_k_m Apache

First-party SmolLM2 1.7B Instruct GGUF artifact pinned by immutable revision, byte size, and SHA-256.
Last Release on Aug 2, 2026