nanbeige · Ollama

ndavat/Nanbeige4.2-3B

949 Pulls 1 Tag Updated 2 weeks ago

ndavat/ndavat-Nanbeige4.2-3B

178 Pulls 1 Tag Updated 2 weeks ago

tomng/nanbeige4.1

Nanbeige4.1-3B illustrates that compact models can simultaneously achieve robust reasoning, preference alignment, and effective agentic behaviors

tools thinking 3b

7,035 Pulls 6 Tags Updated 5 months ago

fauxpaslife/nanbeige4.1

3B model that shouldn't be this good - crushes benchmarks through deep chain-of-thought reasoning

1,801 Pulls 1 Tag Updated 5 months ago

kwangsuklee/Nanbeige4.1-3B.Q4_K_M

26.2.27. Nanbeige4.1-3B-Q4 illustrates that compact models can simultaneously achieve robust reasoning, preference alignment, and effective agentic behaviors.

tools thinking

807 Pulls 1 Tag Updated 5 months ago

fauxpaslife/nanbeige4.1-python-deepthink

Fine-tuned version of Nanbeige 4.1 3B specialized for Python code generation with direct, focused output.

3b

750 Pulls 3 Tags Updated 5 months ago

softw8/Nanbeige4.1-3B-q4_K_M

Nanbeige4.1-3B-q4_K_M no think tools fit 4G-6G GPU OpenClaw local free tokens LobsterAI

tools

444 Pulls 1 Tag Updated 4 months ago

isotnek/Nanbeige4.1-3B-heretic

Ollama version of de-censored Nanbeige4.1-3B-heretic

400 Pulls 1 Tag Updated 5 months ago

iambpn/nanbeige4.1-3B

Optimized its system prompt and parameters for not to overthink too much.

337 Pulls 1 Tag Updated 5 months ago

softw8/nanbeige4.1-3b-tools

nanbeige4.1-3b-tools no think fit 4G-6G GPU OpenClaw local free tokens

tools thinking

212 Pulls 1 Tag Updated 4 months ago

softw8/nanbeige3b-tools-gpu-4g-openclaw

tools thinking

107 Pulls 1 Tag Updated 4 months ago

nuominecraft/nanbeige4.1-3B

59 Pulls 1 Tag Updated 5 months ago

softw8/nanbeige3b-tools-gpu

tools thinking

36 Pulls 1 Tag Updated 4 months ago

softw8/nanbeige4.1-3b-awq

tools thinking

32 Pulls 1 Tag Updated 4 months ago

rouge/nanbeige2-16b-chat

The Nanbeige2-16B-Chat is the latest 16B model developed by the Nanbeige Lab, which utilized 4.5T tokens of high-quality training data during the training phase.

147 Pulls 1 Tag Updated 2 years ago

TCYZ/nano

Model şu an beta aşamasındadır. 1M parametrenin getirdiği sınırlardan dolayı karmaşık cümle yapılarında bozulmalar yaşanabilir. Geliştirme süreci devam etmektedir.

1m 1.2m

22 Pulls 3 Tags Updated 6 months ago

nate/instinct

Instinct is Continue's state-of-the-art open Next Edit model. Robustly fine-tuned from Qwen2.5-Coder-7B, Instinct intelligently predicts your next move to keep you in flow.

tools

6,737 Pulls 1 Tag Updated 11 months ago

azerdsq/g0-nano-base

A 62M-parameter GPT trained from scratch on a single 8GB-RAM NVIDIA Jetson, offering a compact open-weights base model for raw text completion. Not instruction-tuned.

1 Pull 1 Tag Updated 1 week ago

huihui_ai/nemotron-abliterated

Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.

tools 70b

3,052 Pulls 6 Tags Updated 1 year ago