Bielik GGUF models

125 GGUF models in the Bielik family, quantized by 44 uploaders. Sizes run from 21M to 11.2B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
BI
Bielik-11B-v3.0-Instruct
Bielik · speakleash
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik 7B Instruct v0.1
Bielik · speakleash
Params7.24B
Context4K
Q4_K_M4.4 GB
GGUF
BI
Bielik 11B v2.3 Instruct
Bielik · speakleash
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik 11B v2.2 Instruct
Bielik · bartowski
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik Minitron 7B v3.0 Instruct
Bielik · speakleash
Params7.48B
Context32K
Q4_K_M4.5 GB
GGUF
BI
Bielik 7B Instruct v0.1
Bielik · mradermacher
Params7.24B
Context4K
Q4_K_M4.4 GB
GGUF
BI
bielik 4.5b v3 matura history sft2
Bielik · SlayerLab
Params4.76B
Context—
Smallest0.0 GB
GGUF
BI
Bielik-4.5B-v3.0-Instruct
Bielik · speakleash
Params4.76B
Context8K
Smallest5.1 GB
GGUF
BI
Bielik 11B v3.0 Instruct
Bielik · bartowski
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik 7B Instruct v0.1
Bielik · QuantFactory
Params7.24B
Context4K
Q4_K_M4.4 GB
GGUF
BI
Bielik 11B v2.2 Instruct
Bielik · speakleash
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik-1.5B-v3.0-Instruct
Bielik · speakleash
Params1.6B
Context8K
Smallest1.7 GB
GGUF
BI
Bielik 11B v2.2 Instruct
Bielik · QuantFactory
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik Minitron 7B v3.0 Instruct Heretic
Bielik · mradermacher
Params7.48B
Context32K
Q4_K_M4.5 GB
GGUF
BI
Bielik 7B v0.1
Bielik · QuantFactory
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
BI
Bielik 1.5B v3.0 Instruct
Bielik · second-state
Params1.6B
Context8K
Q4_K_M1.0 GB
GGUF
BI
Bielik SOLAR LIKE 10.7B Instruct v0.1
Bielik · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
BI
Basal 2.0 4.5B
Bielik · Remek
Params4.76B
Context32K
Smallest3.4 GB
GGUF
BI
Bielik 4.5B v3.0 Instruct
Bielik · second-state
Params4.76B
Context8K
Q4_K_M2.9 GB
GGUF
BI
Bielik Minitron 7B v3.0 Instruct Ungated
Bielik · mradermacher
Params7.48B
Context32K
Q4_K_M4.5 GB
GGUF
BI
Bielik 11B v2.3 Instruct
Bielik · QuantFactory
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik PL 11B v3.0 Instruct Ungated
Bielik · mradermacher
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
bielik 1.5b v3 matura history sft2
Bielik · SlayerLab
Params1.6B
Context8K
Q4_K_M1.0 GB
GGUF
BI
Bielik 7B v0.1
Bielik · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
BI
Bielik 11B v3.0 Medadapt
Bielik · mradermacher
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik 11B v2
Bielik · QuantFactory
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik 11B v2.2 Instruct GGUF IQ Imatrix
Bielik · speakleash
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik PL 11B v3.0 Instruct Heretic
Bielik · mradermacher
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
BI
Bielik PL Minitron 7B v3.0 Instruct Ungated
Bielik · mradermacher
Params7.48B
Context32K
Q4_K_M4.5 GB
GGUF
BI
Bielik 4.5B v3 Heretic
Bielik · mradermacher
Params4.76B
Context32K
Q4_K_M2.9 GB
GGUF

About the Bielik GGUF models

Bielik is represented on ggufmodels.com by 125 GGUF models, quantized by 44 uploaders on Hugging Face. The most downloaded are Bielik-11B-v3.0-Instruct, Bielik 7B Instruct v0.1 and Bielik 11B v2.3 Instruct. Parameter counts run from 21M to 11.2B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Bielik model is between 1.0 to 6.7 GB, which is the quant most people start with. Most files come from mradermacher (41), speakleash (15) and tensorblock (5). The quants you will meet most often are Q4_K_M (90), Q6_K (85), Q5_K_M (84) and Q8_0 (81), where the number is how many models offer that quant.

Frequently asked questions

Which Bielik GGUF should I download?

The most downloaded Bielik GGUF here is Bielik-11B-v3.0-Instruct. 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 Bielik model need?

Q4_K_M files of Bielik models on this site range from 1.0 to 6.7 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 Bielik GGUF files come from?

The most common quantizers here are mradermacher, speakleash 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