Kanana GGUF models

152 GGUF models in the Kanana family, quantized by 92 uploaders. Sizes run from 1.29B to 30.7B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
KA
Kanana 1.5 15.7b A3B Instruct
Kanana · mradermacher
Params15.7B
Context32K
Q4_K_M10.4 GB
Tool use
KA
Kakaocorp.Kanana 1.5 8b Instruct 2505
Kanana · DevQuasar
Params8.03B
Context32K
Q4_K_M4.9 GB
Tool use
KA
Kanana 1.5 8b Instruct 2505
Kanana · mradermacher
Params8.03B
Context32K
Q4_K_M4.9 GB
Tool use
KA
Kakaocorp.Kanana 1.5 2.1b Instruct 2505
Kanana · DevQuasar
Params2.32B
Context32K
Q4_K_M1.5 GB
Tool use
KA
Kanana 2 3b Instruct
Kanana · mradermacher
Params3.51B
Context32K
Q4_K_M2.2 GB
ReasoningTool use
KA
Kanana 1.5 15.7b A3B Instruct
Kanana · mradermacher
Params15.7B
Context32K
Q4_K_M10.4 GB
Tool use
KA
Kanana 1.5 8b Base
Kanana · mradermacher
Params8.03B
Context32K
Q4_K_M4.9 GB
GGUF
KA
Kanana 1.5 8b Instruct 2505 Rag
Kanana · mradermacher
Params8.03B
Context32K
Q4_K_M4.9 GB
Tool use
KA
Kanana 2 30B A3B Instruct
Kanana · ohora23
Params30.7B
Context32K
Q4_K_M18.6 GB
ReasoningTool use
KA
kanana
Kanana · DKTechin
Params3.51B
Context32K
Q4_K_M2.2 GB
ReasoningTool use
KA
Kanana 2 3b Base
Kanana · mradermacher
Params3.18B
Context32K
Q4_K_M2.0 GB
GGUF
KA
Kanana Nano 2.1b Instruct Ko Reasoning
Kanana · mradermacher
Params2.32B
Context8K
Q4_K_M1.5 GB
ReasoningTool use
KA
Kanana 2 1.3b Embedding
Kanana · mykor
Params1.29B
Context4K
Q4_K_M0.9 GB
CodingEmbedding
KA
Kanana 2 3b Embedding
Kanana · mykor
Params3.18B
Context4K
Q4_K_M2.0 GB
CodingEmbedding
KA
Kanana Safeguard Siren 8b
Kanana · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
KA
Kanana 2 30b a3b instruct 2601
Kanana · deul
Params30.7B
Context32K
Q4_K_M18.6 GB
ReasoningTool use
KA
haru kanana 8b
Kanana · ruddls030
Params8.03B
Context32K
Q4_K_M4.9 GB
RoleplayTool use
KA
Kanana 1.5 2.1b Base
Kanana · mradermacher
Params2.09B
Context32K
Q4_K_M1.4 GB
GGUF
KA
Kanana 1.5 8b Instruct 2505
Kanana · mradermacher
Params8.03B
Context32K
Q4_K_M4.9 GB
Tool use
KA
Kanana 2 3b Instruct
Kanana · mradermacher
Params3.51B
Context32K
Q4_K_M2.2 GB
ReasoningTool use
KA
Kanana Nano 2.1b Instruct
Kanana · mradermacher
Params2.09B
Context8K
Q4_K_M1.4 GB
GGUF
KA
Kanana 1.5 8b Instruct 2505
Kanana · augustine223
Params8.03B
Context32K
Q4_K_M4.9 GB
Tool use
KA
Kanana 2 30b A3B Thinking 2601
Kanana · mykor
Params30.7B
Context32K
Q4_K_M18.6 GB
ReasoningTool use
KA
kanana-1.5-8b-instruct-2505
Kanana · Mungert
Params8.03B
Context32K
Q4_K_M5.0 GB
Tool use
KA
Kanana Nano 2.1b Base
Kanana · mradermacher
Params2.09B
Context8K
Q4_K_M1.4 GB
GGUF
KA
Kanana Nano 2.1b Instruct Abliterated
Kanana · mradermacher
Params2.09B
Context8K
Q4_K_M1.4 GB
GGUF
KA
Kanana 2 1.3b Instruct
Kanana · winwinplatform
Params1.29B
Context32K
Q4_K_M0.9 GB
ReasoningTool use
KA
Kanana 1.5 8b Instruct 2505 Persona Merged
Kanana · mradermacher
Params8.03B
Context32K
Q4_K_M4.9 GB
Tool use
KA
Kanana 2 30b Instruct Abl
Kanana · mradermacher
Params30.7B
Context32K
Q4_K_M18.6 GB
ReasoningTool use
KA
Kakaocorp.Kanana Nano 2.1b Instruct
Kanana · DevQuasar
Params2.09B
Context8K
Q4_K_M1.4 GB
GGUF

About the Kanana GGUF models

Kanana is represented on ggufmodels.com by 152 GGUF models, quantized by 92 uploaders on Hugging Face. The most downloaded are Kanana 1.5 15.7b A3B Instruct, Kakaocorp.Kanana 1.5 8b Instruct 2505 and Kanana 1.5 8b Instruct 2505. Parameter counts run from 1.29B to 30.7B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Kanana model is between 0.9 to 18.6 GB, which is the quant most people start with. Most files come from mradermacher (30), tensorblock (8) and DevQuasar (7). The quants you will meet most often are Q4_K_M (119), Q5_K_M (52), Q8_0 (51) and Q6_K (49), where the number is how many models offer that quant.

Frequently asked questions

Which Kanana GGUF should I download?

The most downloaded Kanana GGUF here is Kanana 1.5 15.7b A3B 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 Kanana model need?

Q4_K_M files of Kanana models on this site range from 0.9 to 18.6 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 Kanana GGUF files come from?

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