Bagel GGUF models

84 GGUF models in the Bagel family, quantized by 20 uploaders. Sizes run from 1.1B to 60.8B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
BA
bagel 34b v0.5 i1
Bagel · mradermacher
Params34.4B
Context195K
Q4_K_M21.2 GB
CodingRoleplayTool use
BA
bagel dpo 34b v0.5 i1
Bagel · mradermacher
Params34.4B
Context195K
Q4_K_M21.2 GB
CodingRoleplayTool use
BA
bagel dpo 20b v04 i1
Bagel · mradermacher
Params19.9B
Context32K
Q4_K_M12.7 GB
CodingRoleplayTool use
BA
bagel dpo 20b v04
Bagel · mradermacher
Params19.9B
Context32K
Q4_K_M12.7 GB
CodingRoleplayTool use
BA
bagel 8b v1.0 i1
Bagel · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
CodingRoleplayTool use
BA
bagel
Bagel · calcuis
Params14.6B
Context—
Q4_K_M8.9 GB
GGUF
BA
bagel 34b v0.5
Bagel · mradermacher
Params34.4B
Context195K
Q4_K_M21.2 GB
CodingRoleplayTool use
BA
jondurbin_bagel-dpo-7b-v0.1
Bagel · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
BA
bagel 7b v0.5
Bagel · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingRoleplayTool use
BA
Bagel Dpo 8x7b v0.2
Bagel · bartowski
Params46.7B
Context32K
Q4_K_M28.4 GB
CodingRoleplay
BA
weyaxi_bagel-hermes-2x34b
Bagel · TheBloke
Params60.8B
Context195K
Q4_K_M36.7 GB
Tool use
BA
bagel dpo 34b v0.5
Bagel · mradermacher
Params34.4B
Context195K
Q4_K_M21.2 GB
CodingRoleplayTool use
BA
bagel 20b v04
Bagel · mradermacher
Params19.9B
Context32K
Q4_K_M12.7 GB
CodingRoleplayTool use
BA
Bagel Hermes 2x34B i1
Bagel · mradermacher
Params60.8B
Context195K
Q4_K_M36.7 GB
Tool use
BA
Bagel Dpo 7b v0.5
Bagel · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingRoleplayTool use
BA
bagel 8b v1.0
Bagel · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
CodingRoleplayTool use
BA
bagel dpo 34b v0.2
Bagel · Artefact2
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
BA
Bagel Dpo 7b v0.1
Bagel · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
BA
Bagel Dpo 1.1b v0.3
Bagel · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
CodingRoleplay
BA
Bagel Dpo 8x7b v0.2
Bagel · mradermacher
Params46.7B
Context32K
Q4_K_M28.4 GB
CodingRoleplay
BA
jondurbin_bagel-dpo-34b-v0.2
Bagel · TheBloke
Params34.4B
Context195K
Q4_K_M20.7 GB
CodingRoleplay
BA
Bagel 7b v0.1
Bagel · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
BA
Bagel Dpo 7b v0.1
Bagel · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
BA
Bagel Dpo 7b v0.4
Bagel · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingRoleplayTool use
BA
Bagel Dpo 7b v0.5
Bagel · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingRoleplayTool use
BA
Bagel 34b v0.2
Bagel · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
CodingRoleplay
BA
Bagel 1.1b v0.3
Bagel · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
CodingRoleplay
BA
bagel-8b-v1.0
Bagel · duyntnet
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
BA
Bagel 7b v0.4
Bagel · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingRoleplayTool use
BA
bagel 34b v0.4 iMat
Bagel · dranger003
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF

About the Bagel GGUF models

Bagel is represented on ggufmodels.com by 84 GGUF models, quantized by 20 uploaders on Hugging Face. The most downloaded are bagel 34b v0.5 i1, bagel dpo 34b v0.5 i1 and bagel dpo 20b v04 i1. Parameter counts run from 1.1B to 60.8B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a Bagel model is between 0.7 to 36.7 GB, which is the quant most people start with. Most files come from mradermacher (36), RichardErkhov (8) and TheBloke (7). The quants you will meet most often are Q2_K (72), Q4_K_M (71), Q6_K (70) and Q3_K_M (69), where the number is how many models offer that quant.

Frequently asked questions

Which Bagel GGUF should I download?

The most downloaded Bagel GGUF here is bagel 34b v0.5 i1. 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 Bagel model need?

Q4_K_M files of Bagel models on this site range from 0.7 to 36.7 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 Bagel GGUF files come from?

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