Openthinker GGUF models

88 GGUF models in the Openthinker family, quantized by 22 uploaders. Sizes run from 1.54B to 32.8B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
OP
open thoughts OpenThinker2 7B
Openthinker · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
OP
OpenThinker Agent v1
Openthinker · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingReasoningTool use
OP
OpenThinker2 32B
Openthinker · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
OP
OpenThinker 7B
Openthinker · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
OP
OpenThinker Agent v1
Openthinker · bartowski
Params8.2B
Context40K
Q4_K_M5.0 GB
Coding
OP
open thoughts OpenThinker 32B
Openthinker · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
OP
OpenThinker3 7B
Openthinker · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
OP
OpenThinker Agent v1 SFT
Openthinker · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingReasoningTool use
OP
OpenThinker2 Off policy GRPO 7B i1
Openthinker · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
OP
OpenThinker2 32B Uncensored
Openthinker · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
OP
open thoughts.OpenThinker 7B Unverified
Openthinker · csabakecskemeti
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
OP
OpenThinker Agent v1
Openthinker · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingReasoningTool use
OP
OpenThinker2 32B
Openthinker · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
OP
OpenThinker2 Offline GRPO 7B
Openthinker · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
OP
OpenThinker 32B Unverified
Openthinker · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
OP
OpenThinker Agent v1 SFT
Openthinker · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingReasoningTool use
OP
OpenThinker2 Offline GRPO 7B i1
Openthinker · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
OP
OpenThinker 7B i1
Openthinker · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
OP
OpenThinker 32B Unverified
Openthinker · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
OP
Huihui ai.OpenThinker 7B Abliterated
Openthinker · DevQuasar-7
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
OP
OpenThinker2 32B Uncensored
Openthinker · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
OP
OpenThinker2 7B i1
Openthinker · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
OP
open thoughts.OpenThinker 7B
Openthinker · DevQuasar-8
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
OP
OpenThinker2 Off policy GRPO 7B
Openthinker · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
OP
Open thoughts.OpenThinker 32B Unverified
Openthinker · DevQuasar-8
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
OP
OpenThinker3 1.5B RLVE i1
Openthinker · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
OP
OpenThinker3 1.5B
Openthinker · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
OP
OpenThinker3 1.5B i1
Openthinker · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
OP
Open thoughts.OpenThinker3 7B
Openthinker · DevQuasar
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
OP
Open thoughts.OpenThinker2 32B
Openthinker · DevQuasar-12
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use

About the Openthinker GGUF models

Openthinker is represented on ggufmodels.com by 88 GGUF models, quantized by 22 uploaders on Hugging Face. The most downloaded are open thoughts OpenThinker2 7B, OpenThinker Agent v1 and OpenThinker2 32B. Parameter counts run from 1.54B to 32.8B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Openthinker model is between 1.0 to 19.9 GB, which is the quant most people start with. Most files come from mradermacher (35), roleplaiapp (14) and bartowski (6). The quants you will meet most often are Q4_K_M (62), Q6_K (58), Q2_K (55) and Q3_K_L (54), where the number is how many models offer that quant.

Frequently asked questions

Which Openthinker GGUF should I download?

The most downloaded Openthinker GGUF here is open thoughts OpenThinker2 7B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Openthinker model need?

Q4_K_M files of Openthinker models on this site range from 1.0 to 19.9 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Openthinker GGUF files come from?

The most common quantizers here are mradermacher, roleplaiapp and bartowski. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing