Upload 4 files

README.md

@@ -1,3 +1,31 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+inference: false 
+base_model: Qwen/Qwen3-8B-Instruct
+base_model_relation: quantized 
+tags: [green, llmware-chat, p8, gguf,emerald]
+---
+
+# qwen3-8b-instruct-gguf
+
+**qwen3-8b-instruct-gguf** is a GGUF Q4_K_M int4 quantized version of [Qwen3-8B](https://www.huggingface.co/Qwen/Qwen3-8B), providing a very fast inference implementation, optimized for AI PCs.    
+
+### Model Description
+
+- **Developed by:** Qwen
+- **Model type:** qwen3
+- **Parameters:** 8 billion  
+- **Model Parent:** Qwen/Qwen3-8B  
+- **Language(s) (NLP):** English  
+- **License:** Apache 2.0  
+- **Uses:** Chat, general-purpose LLM  
+- **Quantization:** int4  
+  
+
+## Model Card Contact  
+
+[llmware on github](https://www.github.com/llmware-ai/llmware) 
+
+[llmware on hf](https://www.huggingface.co/llmware)  
+
+[llmware website](https://www.llmware.ai)  

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

hash_record_sha256.json

@@ -0,0 +1,4 @@
+{
+ "Qwen3-8B-Q4_K_M.gguf": "d98cdcbd03e17ce47681435b5150e34c1417f50b5c0019dd560e4882c5745785",
+ "time_stamp": "2025-07-05_144722"
+}

qwen3-8b-gguf.md

@@ -0,0 +1,31 @@
+---
+license: apache-2.0
+inference: false 
+base_model: Qwen/Qwen3-8B-Instruct
+base_model_relation: quantized 
+tags: [green, llmware-chat, p8, gguf,emerald]
+---
+
+# qwen3-8b-instruct-gguf
+
+**qwen3-8b-instruct-gguf** is a GGUF Q4_K_M int4 quantized version of [Qwen3-8B](https://www.huggingface.co/Qwen/Qwen3-8B), providing a very fast inference implementation, optimized for AI PCs.    
+
+### Model Description
+
+- **Developed by:** Qwen
+- **Model type:** qwen3
+- **Parameters:** 8 billion  
+- **Model Parent:** Qwen/Qwen3-8B  
+- **Language(s) (NLP):** English  
+- **License:** Apache 2.0  
+- **Uses:** Chat, general-purpose LLM  
+- **Quantization:** int4  
+  
+
+## Model Card Contact  
+
+[llmware on github](https://www.github.com/llmware-ai/llmware) 
+
+[llmware on hf](https://www.huggingface.co/llmware)  
+
+[llmware website](https://www.llmware.ai)