Open GGUF models

117 GGUF models in the Open family, quantized by 36 uploaders. Sizes run from 135M to 65B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
OP
rombodawg_open_gpt4_8x7b
Open · TheBloke
Params46.7B
Context32K
Q4_K_M26.4 GB
GGUF
OP
rombodawg_open_gpt4_8x7b_v0.2
Open · TheBloke
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
OP
s4sch_open-hermes-2.5-neural-chat-3.1-frankenmerge-11b
Open · TheBloke
Params11.4B
Context32K
Q4_K_M6.8 GB
Tool use
OP
allenai_open-instruct-human-mix-65b
Open · TheBloke
Params65B
Context2K
Q4_K_M39.3 GB
GGUF
OP
knoveleng Open RS3
Open · bartowski
Params1.78B
Context128K
Q4_K_M1.1 GB
GGUF
OP
Open R1 Math 7B Instruct
Open · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
OP
Open R1 Mini Experimental
Open · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
ReasoningVision
OP
Open R1 Math 7B Instruct
Open · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
OP
Open R1 Video 7B
Open · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningVision
OP
open cabrita3b
Open · lucianosb
Params3.55B
Context—
Smallest2.1 GB
GGUF
OP
Open R1 Mini Experimental
Open · prithivMLmods
Params1.54B
Context32K
Q4_K_M1.0 GB
ReasoningVision
OP
open-calm-7b
Open · mmnga
Params6.87B
Context2K
Q4_K_M4.4 GB
GGUF
OP
Open Reasoner Zero 7B
Open · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
OP
open neo.DeepNeo 1 8B Preview
Open · csabakecskemeti
Params8.02B
Context32K
Q4_K_M4.9 GB
Tool use
OP
OPEN SOLAR KO 10.7B
Open · MaziyarPanahi
Params10.9B
Context2K
Q4_K_M6.5 GB
GGUF
OP
Open R1 Mini Experimental
Open · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
Reasoning
OP
Open1 1.5B Instruct
Open · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
Tool use
OP
Open StarLake Swap 7B
Open · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OP
open-calm-1b
Open · mmnga
Params1.42B
Context2K
Q4_K_M0.9 GB
GGUF
OP
allenai.open instruct code alpaca 7b
Open · DevQuasar-7
Params6.74B
Context2K
Q4_K_M4.1 GB
Coding
OP
Open Instruct Stanford Alpaca 7b
Open · RichardErkhov
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
OP
Open Xi Math Preview
Open · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
OP
open-calm-3b
Open · mmnga
Params2.79B
Context2K
Q4_K_M1.8 GB
GGUF
OP
prithivMLmods.Open R1 Mini Experimental
Open · DevQuasar-7
Params1.54B
Context32K
Q4_K_M1.0 GB
Reasoning
OP
Open RS3
Open · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
OP
Open LiveTranslate v0 En Zh
Open · mradermacher
Params30.5B
Context64K
Q4_K_M18.6 GB
ReasoningTool useVision
OP
Open Reasoner Zero 7B
Open · brittlewis12
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
OP
Open Gpt4 8x7B v0.2
Open · mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
GGUF
OP
Open1 7.5B Instruct
Open · mradermacher
Params7.46B
Context32K
Q4_K_M4.6 GB
Tool use
OP
open cabrita3b i1
Open · mradermacher
Params3.55B
Context2K
Q4_K_M2.7 GB
GGUF

About the Open GGUF models

Open is represented on ggufmodels.com by 117 GGUF models, quantized by 36 uploaders on Hugging Face. The most downloaded are rombodawg_open_gpt4_8x7b, rombodawg_open_gpt4_8x7b_v0.2 and s4sch_open-hermes-2.5-neural-chat-3.1-frankenmerge-11b. Parameter counts run from 135M to 65B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Open model is between 0.1 to 39.3 GB, which is the quant most people start with. Most files come from mradermacher (49), tensorblock (12) and RichardErkhov (7). The quants you will meet most often are Q2_K (95), Q4_K_M (89), Q5_K_M (83) and Q3_K_M (83), where the number is how many models offer that quant.

Frequently asked questions

Which Open GGUF should I download?

The most downloaded Open GGUF here is rombodawg_open_gpt4_8x7b. 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 Open model need?

Q4_K_M files of Open models on this site range from 0.1 to 39.3 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 Open GGUF files come from?

The most common quantizers here are mradermacher, tensorblock and RichardErkhov. 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