Reach me on X DMs OR ollama discord for suggesting models and reporting bugs.
-
Mistral-Small3.1-24B-Instruct-2503
Mistral Small 3.1
15.1K Pulls 7 Tags Updated 13 days ago
-
qihoo360-TinyR1-32b-preview
SuperDistillation Achieves Near-R1 Performance with Just 5% of Parameters, available in [F16, q8_0, q6_K, q4_K_S]
tools561 Pulls 4 Tags Updated 4 weeks ago
-
Qwen2.5-Coder-32B-Instruct
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models available in [F16, q8_0, q6_K, q4_K_S]
tools482 Pulls 4 Tags Updated 6 weeks ago
-
nvidia_Llama-3.3-Nemotron-Super-49B-v1
reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling.
471 Pulls 6 Tags Updated 13 days ago
-
unsloth-QwQ-32B
Qwen-QwQ-32B with UNSLOTH bug fixes.
tools467 Pulls 8 Tags Updated 3 weeks ago
-
Unsloth_gemma3-27b-it
Unsloth finetune of gemma 3
vision328 Pulls 7 Tags Updated 2 weeks ago
-
open-r1_OlympicCoder-32B
Qwen2.5-Coder-32B-Instruct fine-tuned on a decontaminated version of the codeforces dataset.
tools301 Pulls 7 Tags Updated 2 weeks ago
-
Unsloth-Phi-4-mini-instruct
Phi-4-mini-instruct with Unsloth fixes, works on ollama v0.5.13-rc4, available in [F16, q8_0]
tools287 Pulls 2 Tags Updated 4 weeks ago
-
Unsloth_gemma3-4b-it
Unsloth finetune of gemma 3
vision269 Pulls 7 Tags Updated 2 weeks ago
-
Unsloth_gemma3-12b-it
Unsloth finetune of gemma 3
vision252 Pulls 7 Tags Updated 2 weeks ago
-
DeepSeek-R1-Distill-Llama-8B-NexaQuant
DeepSeek R1 Distilled model to one-fourth its original file size—without losing any accuracy.
243 Pulls 1 Tag Updated 5 weeks ago
-
OpenThinker-32B
fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the OpenThoughts-114k dataset, available in [F16, q8_0, q6_K, q4_K_S]
tools221 Pulls 4 Tags Updated 6 weeks ago
-
Qwen2.5-Coder-32B-Instruct-Roo
Qwen2.5-Coder for Roo available in [F16, q8_0, q6_K, q4_K_S]
tools191 Pulls 4 Tags Updated 5 weeks ago
-
llm4decompile-22b-v2
LLM4Decompile aims to decompile x86 assembly instructions into C. available in [F16, q8_0, q6_K, q4_K_S]
174 Pulls 4 Tags Updated 6 weeks ago
-
QwQ-32B-0305
reasoning model of the Qwen series.
tools119 Pulls 4 Tags Updated 3 weeks ago
-
Arcee-Blitz-24b-Instruct
Arcee-Blitz (24B) is a new Mistral-based 24B model distilled from DeepSeek, available in [F16, q8_0, q6_K, q4_K_S]
91 Pulls 4 Tags Updated 5 weeks ago
-
Unsloth_gemma3-1b-it
Unsloth finetune of gemma 3
vision85 Pulls 6 Tags Updated 2 weeks ago
-
sbintuitions-sarashina2.2-3b-instruct-v0.1
Japanese language models trained by SB Intuitions, available in [F16, q8_0, q6_K, q4_K_S]
tools83 Pulls 4 Tags Updated 3 weeks ago
-
allenai_OLMo2-0325-32B-Instruct
OLMo 2 32B Instruct March 2025
81 Pulls 2 Tags Updated 2 weeks ago
-
LGAI_EXAONE-Deep-7.8B
EXAONE Deep by LG AI Research.
78 Pulls 7 Tags Updated 13 days ago
-
s1.1-32B
a reasoning model finetuned from Qwen2.5-32B-Instruct on just 1,000 examples. It matches o1-preview & exhibits test-time scaling via budget forcing. available in [F16, q8_0, q6_K, q4_K_S]
tools71 Pulls 4 Tags Updated 6 weeks ago
-
Mistral-Small-24B-Instruct-2501-writer
fine-tuned version of mistralai/Mistral-Small-24B-Instruct-2501, optimized specifically for creative writing tasks. by **lars1234**
66 Pulls 7 Tags Updated 3 weeks ago
-
DeepScaleR-1.5B-Preview
DeepScaleR-1.5B-Preview is a language model fine-tuned from DeepSeek-R1-Distilled-Qwen-1.5B using distributed reinforcement learning (RL)
63 Pulls 1 Tag Updated 5 weeks ago
-
UIGEN-T1-Qwen-7b
UIGEN-T1 is a fine-tuned Qwen2.5-Coder-7B-Instruct model. It is designed for reasoning-based UI generation, leveraging a complex chain-of-thought approach to produce robust HTML and CSS-based UI components.
tools59 Pulls 1 Tag Updated 5 weeks ago
-
UIGEN-T1-Qwen-14
UIGEN-T1 is a fine-tuned Qwen2.5-Coder-14B-Instruct model. designed for reasoning-based UI generation. available in [F16, q8_0, q6_K, q4_K_S]
tools58 Pulls 4 Tags Updated 5 weeks ago
-
LGAI_EXAONE-Deep-32B
EXAONE Deep by LG AI Research.
50 Pulls 7 Tags Updated 13 days ago
-
DeepSeek-R1-Distill-Llama-3.1-16.5B-Brainstorm
Brainstorm 40x by DavidAU available in [F16, q8_0, q6_K, q4_K_S]
49 Pulls 4 Tags Updated 4 weeks ago
-
qihoo360-Light-R1-32B
Qwen2.5-32B-Instruct finetune surpassing R1-Distill from Scratch
tools49 Pulls 7 Tags Updated 3 weeks ago
-
OpenPipe_Deductive-Reasoning-Qwen-32B
Deductive Reasoning Qwen 32B is a reinforcement fine-tune of Qwen 2.5 32B Instruct to solve challenging deduction problems
tools44 Pulls 7 Tags Updated 2 weeks ago
-
LGAI_EXAONE-Deep-2.4B
EXAONE Deep by LG AI Research.
42 Pulls 7 Tags Updated 13 days ago
-
Reverb-7b
Reverb-7b is a 7 billion parameter language model developed by Ozone AI. available in [F16, q8_0, q6_K, q4_K_S]
tools18 Pulls 4 Tags Updated 5 weeks ago
-
AceMath-72B-Instruct
model excel at solving English mathematical problems using Chain-of-Thought (CoT) reasoning available in [F16, q8_0, q6_K, q4_K_S]
13 Pulls 4 Tags Updated 6 weeks ago
-
ilsp-Llama-Krikri-8B-Instruct
LLM for the Greek language,available in [F16, q8_0, q6_K, q4_K_S]
tools9 Pulls 4 Tags Updated 3 weeks ago
-
Steelskull-L3.3-Cu-Mai-R1-70b
available in [F16, q8_0, q6_K, q4_K_S]
tools8 Pulls 4 Tags Updated 4 weeks ago