Next GGUF models

127 GGUF models in the Next family, quantized by 8 uploaders. Sizes run from 268M to 70.6B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
NE
Next 1b
Next · mattritchey
Params1B
Context32K
Q4_K_M0.8 GB
Coding
NE
Next2.5
Next · thelamapi
Params4.2B
Context256K
Q4_K_M2.7 GB
ReasoningVision
NE
Next 12b
Next · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Coding
NE
Next 8b
Next · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
Reasoning
NE
Next Ocr
Next · thelamapi
Params8.19B
Context256K
Smallest8.7 GB
CodingVision
NE
Next 14b
Next · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
NE
Next 32b
Next · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
NE
Next Ocr
Next · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
CodingTool useVision
NE
Next 8b
Next · Lamapi
Params8.19B
Context128K
Q4_K_M5.0 GB
Reasoning
NE
Next 1b
Next · thelamapi
Params1B
Context32K
Smallest1.1 GB
Coding
NE
Next 4b
Next · Lamapi
Params3.88B
Context128K
Q4_K_M2.5 GB
CodingVision
NE
Next 12b
Next · Lamapi
Params11.8B
Context128K
Q4_K_M7.3 GB
CodingVision
NE
Next 70b
Next · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
NE
Next 12b
Next · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
CodingVision
NE
Next Ocr
Next · Lamapi
Params8.19B
Context256K
Q4_K_M5.0 GB
CodingVision
NE
Next2 Air
Next · thelamapi
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningVision
NE
Next 14b
Next · Lamapi
Params14.8B
Context40K
Q4_K_M9.0 GB
Reasoning
NE
Next2.5
Next · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
NE
Next Ocr
Next · thelamapi
Params8.19B
Context256K
Q4_K_M5.0 GB
CodingTool useVision
NE
Next Ocr
Next · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
CodingTool useVision
NE
Next2 0.8b
Next · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
NE
Next2 0.8b
Next · thelamapi
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
NE
Next 70b
Next · thelamapi
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
NE
Next2 Fast
Next · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
NE
Next2 Air
Next · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
NE
Next2.5
Next · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
NE
Next 1b
Next · mradermacher
Params1B
Context32K
Q4_K_M0.8 GB
Coding
NE
Next 14b
Next · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
NE
Next2 Air
Next · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
NE
Next2 Fast
Next · thelamapi
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision

About the Next GGUF models

Next is represented on ggufmodels.com by 127 GGUF models, quantized by 8 uploaders on Hugging Face. The most downloaded are Next 1b, Next2.5 and Next 12b. Parameter counts run from 268M to 70.6B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Next model is between 0.3 to 42.5 GB, which is the quant most people start with. Most files come from Lamapi (81), mradermacher (21) and thelamapi (15). The quants you will meet most often are Q4_K_M (44), Q2_K (38), Q6_K (37) and Q5_K_M (37), where the number is how many models offer that quant.

Frequently asked questions

Which Next GGUF should I download?

The most downloaded Next GGUF here is Next 1b. 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 Next model need?

Q4_K_M files of Next models on this site range from 0.3 to 42.5 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 Next GGUF files come from?

The most common quantizers here are Lamapi, mradermacher and thelamapi. 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