Breeze GGUF models

90 GGUF models in the Breeze family, quantized by 36 uploaders. Sizes run from 21M to 12.7B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
BR
Breeze-TTS-2
Breeze · HoppouAI
Params3.01B
Context—
Smallest2.5 GB
GGUF
BR
Breeze-ASR-25
Breeze · handy-computer
Params1.54B
Context—
Q4_K_M1.0 GB
GGUF
BR
breeze-tts-2
Breeze · cstr
Params2.85B
Context—
Smallest2.2 GB
GGUF
BR
Breeze-7B-Instruct-v0_1
Breeze · RichardErkhov
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze 7B 32k Instruct V1_0
Breeze · RichardErkhov
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze-13B-32k-Instruct-v1_0
Breeze · mradermacher
Params12.7B
Context32K
Q4_K_M7.7 GB
GGUF
BR
Breeze-7B-Instruct-v1_0
Breeze · mradermacher
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze TTS 2
Breeze · Raxdiam
Params—
Context—
Smallest4.3 GB
GGUF
BR
Breeze TTS 2
Breeze · npario
Params—
Context—
Smallest4.3 GB
GGUF
BR
Breeze 7B 32k Base V1_0
Breeze · RichardErkhov
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze TTS 2
Breeze · agentory
Params—
Context—
Smallest4.3 GB
GGUF
BR
Breeze 7B Instruct v0 1
Breeze · ZoneTwelve
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze-13B-32k-Instruct-v1_0
Breeze · mradermacher
Params12.7B
Context32K
Q4_K_M7.7 GB
GGUF
BR
Breeze-7B-Base-v1_0
Breeze · RichardErkhov
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze Petro 7B Instruct v1 i1
Breeze · mradermacher
Params7.49B
Context32K
Q4_K_M4.5 GB
Coding
BR
Breeze 3b
Breeze · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
BR
Breeze 7B PTT Chat v1
Breeze · mradermacher
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze-7B-Instruct-v1_0
Breeze · RichardErkhov
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze 7B Instruct V1_0
Breeze · second-state
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze 7B Instruct v1 0
Breeze · ZoneTwelve
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze 7B Instruct V0_1
Breeze · mradermacher
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze TTS 2
Breeze · EvoAwaken-Workshop
Params—
Context—
Smallest2.2 GB
GGUF
BR
Breeze 7B 32k Instruct V1_0
Breeze · mradermacher
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze 7B PTT Chat v2
Breeze · mradermacher
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze-13B-32k-Base-v1_0
Breeze · mradermacher
Params12.7B
Context32K
Q4_K_M7.7 GB
GGUF
BR
Breeze 7B Instruct 64k v0.1
Breeze · audreyt
Params7.49B
Context128K
Q4_K_M4.5 GB
GGUF
BR
Breeze 7B Instruct V1_0
Breeze · gaianet
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze 7B Base V0_1
Breeze · RichardErkhov
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
BR
Breeze-TTS-2
Breeze · xuran4502
Params3.01B
Context—
Smallest2.5 GB
GGUF
BR
Breeze 7B Instruct v1 0
Breeze · QuantFactory
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF

About the Breeze GGUF models

Breeze is represented on ggufmodels.com by 90 GGUF models, quantized by 36 uploaders on Hugging Face. The most downloaded are Breeze-TTS-2, Breeze-ASR-25 and breeze-tts-2. Parameter counts run from 21M to 12.7B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Breeze model is between 1.0 to 7.7 GB, which is the quant most people start with. Most files come from mradermacher (28), CHE-72 (11) and RichardErkhov (6). The quants you will meet most often are Q6_K (55), Q4_K_M (55), Q5_K_M (54) and Q8_0 (48), where the number is how many models offer that quant.

Frequently asked questions

Which Breeze GGUF should I download?

The most downloaded Breeze GGUF here is Breeze-TTS-2. 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 Breeze model need?

Q4_K_M files of Breeze models on this site range from 1.0 to 7.7 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 Breeze GGUF files come from?

The most common quantizers here are mradermacher, CHE-72 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