Zephyr GGUF models

250 GGUF models in the Zephyr family, quantized by 70 uploaders. Sizes run from 7M to 141B parameters. The longest trained context is 195K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ZE
huggingfaceh4_zephyr-7b-beta
Zephyr · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr orpo 141b A35b v0.1 GGUF smashed
Zephyr · PrunaAI
Params141B
Context64K
Q4_K_M85.6 GB
GGUF
ZE
Zephyr 7B Beta Harmless
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr 7b hh dpo i1
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr 7b hh dpo
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
Zephyr 7b Beta Abliterated
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr 7b alpha
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
huggingfaceh4_zephyr-7b-alpha
Zephyr · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
Zephyr 7B Beta Harmless
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr 7b beta
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
models--HuggingFaceH4--zephyr-orpo-141b-A35b-v0.1
Zephyr · MaziyarPanahi
Params141B
Context64K
Q4_K_M85.6 GB
GGUF
ZE
zephyr-7b-sft-full-SPIN-iter3
Zephyr · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
models--mergekit-community--mergekit-slerp-jeyctse
Zephyr · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
LORAs
Zephyr · kukidevalml
Params4B
Context40K
Smallest8.1 GB
GGUF
ZE
zephyr 7b beta
Zephyr · QuantFactory
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr 7b beta nf4 fp16 upscaled
Zephyr · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
models--mergekit-community--mergekit-slerp-zzizhry
Zephyr · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr quiklang 3b 4K
Zephyr · TheBloke
Params2.8B
Context4K
Q4_K_M1.7 GB
Tool use
ZE
Zephyr 7b Beta
Zephyr · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr 7b alpha
Zephyr · QuantFactory
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
qblocks_zephyr_7b_norobots
Zephyr · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
ZE
models--mergekit-community--mergekit-slerp-xyweuvi
Zephyr · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
gguf zephyr 220m dpo full
Zephyr · Felladrin
Params218M
Context2K
Q4_K_M0.2 GB
GGUF
ZE
zephyr orpo 141b A35b v0.1 i1
Zephyr · mradermacher
Params141B
Context64K
Smallest29.6 GB
GGUF
ZE
zephyr sumbot all songs small
Zephyr · mradermacher
Params1.64B
Context4K
Q4_K_M1.0 GB
GGUF
ZE
Zephyr 7b Beta Absolute Heresy
Zephyr · mradermacher
Params7.24B
Context64K
Q4_K_M4.4 GB
GGUF
ZE
models--mergekit-community--mergekit-slerp-fodinzo
Zephyr · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr 220m dpo full
Zephyr · afrideva
Params218M
Context2K
Q4_K_M0.1 GB
GGUF
ZE
zephyr quiklang 3b
Zephyr · TheBloke
Params2.8B
Context4K
Q4_K_M1.7 GB
Tool use
ZE
Zephyr 7b Beta Abliterated
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

About the Zephyr GGUF models

Zephyr is represented on ggufmodels.com by 250 GGUF models, quantized by 70 uploaders on Hugging Face. The most downloaded are huggingfaceh4_zephyr-7b-beta, zephyr orpo 141b A35b v0.1 GGUF smashed and Zephyr 7B Beta Harmless. Parameter counts run from 7M to 141B, and the longest trained context window is 195K tokens.

A Q4_K_M file of a Zephyr model is between 0.1 to 85.6 GB, which is the quant most people start with. Most files come from mradermacher (77), RichardErkhov (42) and tensorblock (23). The quants you will meet most often are Q2_K (181), Q4_K_M (178), Q3_K_M (163) and Q5_K_M (162), where the number is how many models offer that quant.

Frequently asked questions

Which Zephyr GGUF should I download?

The most downloaded Zephyr GGUF here is huggingfaceh4_zephyr-7b-beta. 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 Zephyr model need?

Q4_K_M files of Zephyr models on this site range from 0.1 to 85.6 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 Zephyr GGUF files come from?

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