Ice GGUF models

180 GGUF models in the Ice family, quantized by 33 uploaders. Sizes run from 1.24B to 13B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
IC
darkps ice AI
Ice · bartowski
Params8.2B
Context40K
Q4_K_M5.2 GB
GGUF
IC
ice AI i1
Ice · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
IC
Ice0.17 03.10 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.123 28.05 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.129 15.06 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.140 14.10 RP
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.110 04.05 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.27 06.11 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.141 14.10 RP
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.107 04.05 RP ORPO v1 i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
ice AI
Ice · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
IC
Ice0.106 22.04 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.108 04.05 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
ICE GRT i1
Ice · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
IC
Ice0.143 15.10 RP
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.16 02.10 RP
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.107 04.05 RP ORPO v2 i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.147 17.10 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.128 15.06 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.15 06.11 RP orpo i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.113 08.05 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.17 03.10 RP
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.146 17.10 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.148 19.10 RP
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.144 15.10 RP
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.114 09.05 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.125 29.05 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.112 08.05 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.111 08.05 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
IC
Ice0.115 10.05 RP i1
Ice · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay

About the Ice GGUF models

Ice is represented on ggufmodels.com by 180 GGUF models, quantized by 33 uploaders on Hugging Face. The most downloaded are darkps ice AI, ice AI i1 and Ice0.17 03.10 RP i1. Parameter counts run from 1.24B to 13B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Ice model is between 4.4 to 7.9 GB, which is the quant most people start with. Most files come from mradermacher (142), PAUL1122 (4) and youngcho (2). The quants you will meet most often are Q6_K (144), Q5_K_S (144), Q5_K_M (144) and Q4_K_S (144), where the number is how many models offer that quant.

Frequently asked questions

Which Ice GGUF should I download?

The most downloaded Ice GGUF here is darkps ice AI. 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 Ice model need?

Q4_K_M files of Ice models on this site range from 4.4 to 7.9 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 Ice GGUF files come from?

The most common quantizers here are mradermacher, PAUL1122 and youngcho. 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