GGUF models: creativeml-openrail-m license

263 GGUF models listed under the creativeml-openrail-m license on Hugging Face. Always read the license text before commercial use. Sizes run from 40M to 69B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Ollama 3.2
Llama · michelkao
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
LL
Llama Deepsync 3B i1
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
CodingTool use
LL
Llama 3.1 8B Open SFT i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
QW
Qwen2.5 Coder 7b Bnb 4bit
Qwen · prithivMLmods
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
LL
Llama Magpie 3.2 3B Instruct i1
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
TR
Triangulum 1B
Triangulum · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
ReasoningTool use
NO
Novaeus Promptist 7B Instruct
Novaeus · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
QW
QwQ LCoT 3B Instruct
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
ReasoningTool use
TU
Tulu MathLingo 8B i1
Tulu · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
QW
Qwen UMLS 7B Instruct
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
QW
QwQ LCoT 7B Instruct
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
LL
EnnoAi Pro Llama 3 8B v0.3
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
PO
PornMaster
Pornmaster · nuupy
Params2.57B
Context—
Q4_K_M1.6 GB
GGUF
ST
stable diffusion v1 5
Stable · genai-archive
Params1.07B
Context—
Smallest2.1 GB
GGUF
LL
Llama Sentient 3.2 3B Instruct
Llama · prithivMLmods
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
TR
Triangulum 1B
Triangulum · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
ReasoningTool use
MA
Math IIO 7B Instruct
Math · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
ST
stable diffusion v1 4
Stable · gpustack
Params1.07B
Context—
Smallest1.7 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
SM
SmolLM2 135M Instruct
SmolLM · prithivMLmods
Params135M
Context8K
Q4_K_M0.1 GB
GGUF
LL
Llama Deepsync 1B
Llama · QuantFactory
Params1.5B
Context128K
Q4_K_M1.0 GB
CodingTool use
NE
Neumind Math 7B Instruct
Neumind · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
LL
Llama Deepsync 1B i1
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
CodingTool use
LL
Tulu MathLingo 8B
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
SD
SDXL Lightning Quantized
Sdxl · TensorVizion
Params2.57B
Context—
Smallest1.0 GB
GGUF
QW
Qwen2.5 Coder 14B Instruct F16
Qwen · prithivMLmods
Params14.8B
Context32K
Smallest29.5 GB
CodingTool use
QW
Qwen2.5 0.5B 200K
Qwen · prithivMLmods
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
OP
openchatgpt neox 125m
Openchatgpt · mradermacher
Params162M
Context2K
Q4_K_M0.1 GB
GGUF
DE
Deepthink Reasoning 7B Q4 K M
Deepthink · itlwas
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingReasoningTool use

Keep browsing