qwen3:4b_4bit_不思考版，不浪费算力去思考，直接回答。
10K Pulls 4 Tags Updated 7 months ago
From qwen3:4b-instruct:2507
569 Pulls 1 Tag Updated 4 months ago
From qwen3:4b-thinking:2507
166 Pulls 1 Tag Updated 4 months ago
The model Qwen3:4B Fine-Tuned by QAIS that is optimized for coding.
27 Pulls 1 Tag Updated 1 month ago
Alibaba's text embedding model.Qwen3-Embedding-4B has the following features: Model Type: Text Embedding Supported Languages: 100+ Languages Number of Paramaters: 4B Context Length: 32k Embedding Dimension: Up to 2560, supports user-defined output ...
17.4K Pulls 4 Tags Updated 2 months ago
Quantized version of Qwen3 models (4B,8B,14B,32B, 30B-moe) optimized for tool usage in Cline / Roo Code and solving Complex Problems.
10.2K Pulls 8 Tags Updated 7 months ago
Alibaba's text reranking model.Qwen3-Reranker-4B has the following features: Model Type: Text Reranking Supported Languages: 100+ Languages Number of Paramaters: 4B Context Length: 32k...
6,982 Pulls 3 Tags Updated 6 months ago
2,219 Pulls 1 Tag Updated 4 months ago
915 Pulls 1 Tag Updated 4 months ago
This is the Qwen3 4B embedding model from here: https://huggingface.co/Qwen/Qwen3-Embedding-4B
847 Pulls 1 Tag Updated 3 months ago
Alibaba's Qwen3-Coder-30B 4bit with 1M token context. Enhanced tool calling for agentic coding tasks
696 Pulls 1 Tag Updated 4 months ago
use with goose: qwen3 8B 4bit with no_think. GOOSE_PROVIDER=ollama GOOSE_MODEL=michaelneale/qwen3 goose session
617 Pulls 1 Tag Updated 7 months ago
Alibaba's Qwen3-Coder-30B 4bit with 256k token context. Enhanced tool calling for agentic coding tasks
586 Pulls 1 Tag Updated 4 months ago
A small Qwen3 4 billion parameter model trained on nvidia/OpenCodeReasoning for coding tasks.
527 Pulls 1 Tag Updated 7 months ago
deeptranslate-r2-4b 是一个从 qwen3 4b 微调而来的语言模型，专门用于英文和中文之间的高质量翻译。我们的模型使用监督式微调(SFT)技术，在仅有4B参数的计算效率下实现高质量翻译。
515 Pulls 1 Tag Updated 6 months ago
Chinda Opensource Thai LLM 4B is iApp Technology's cutting-edge Thai language model that brings advanced thinking capabilities to the Thai AI ecosystem. Built on the latest Qwen3-4B architecture, represents our commitment to developing Thai sovereign AI.
440 Pulls 1 Tag Updated 6 months ago
Qwen3-4B-Thinking-2507_q8: A 4-billion-parameter inference model with 8-bit quantization, optimized for efficient reasoning in resource-constrained environments.
409 Pulls 1 Tag Updated 3 months ago
Typhoon2.5 4B - 4B parameters Thai / English bilingual LLM build based on Qwen3.
366 Pulls 1 Tag Updated 2 months ago
Spreading the love for https://huggingface.co/Menlo/Jan-nano-gguf. a model fine-tuned with DAPO on Qwen3-4B. Jan-nano Can do deep research, picks up relevant information effectively from search results, and uses tools.
301 Pulls 1 Tag Updated 6 months ago
包含2个量化版本GGUF：Qwen3-4B-Q5_K_M，Qwen3-4B-Q8_0
161 Pulls 2 Tags Updated 6 months ago