Nous GGUF models

71 GGUF models in the Nous family, quantized by 30 uploaders. Sizes run from 1.64B to 69B parameters. The longest trained context is 195K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
NO
nousresearch_nous-capybara-34b
Nous · TheBloke
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
NO
Nous Puffin 70B
Nous · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
NO
nousresearch_nous-capybara-7b-v1.9
Nous · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NO
Nous Hermes 2 SOLAR 10.7B
Nous · TheBloke
Params10.7B
Context4K
Q4_K_M6.5 GB
Tool use
NO
Nous Capybara limarpv3 34B i1
Nous · mradermacher
Params34.4B
Context195K
Q4_K_M21.2 GB
GGUF
NO
Nous Hermes 13B Code
Nous · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
CodingTool use
NO
Nous Puffin 70B i1
Nous · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
NO
nousresearch_nous-hermes-13b
Nous · TheBloke
Params13B
Context2K
Q4_K_M7.9 GB
Tool use
NO
Nous Capybara 34B i1
Nous · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
NO
Nous Capybara 7B
Nous · TheBloke
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
NO
Nous Capybara 34B
Nous · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
NO
doctor-shotgun_nous-capybara-limarpv3-34b
Nous · TheBloke
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
NO
Nous Hermes 2 SOLAR 10.7B
Nous · QuantFactory
Params10.7B
Context4K
Q4_K_M6.5 GB
Tool use
NO
Nous Hermes 2 SUS Chat 34B Slerp
Nous · TheBloke
Params34.4B
Context4K
Q4_K_M20.7 GB
Tool use
NO
Nous Hermes 2 Mixtruct v0.1 8x7B DPO DARE TIES iMat
Nous · InferenceIllusionist
Params46.7B
Context32K
Q4_K_M28.4 GB
Tool use
NO
Nous Puffin 70B
Nous · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
NO
Nous Hermes ReflexAgent 8B v1
Nous · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
NO
Nous Hermes 2 SOLAR 10.7B i1
Nous · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
Tool use
NO
Nous-Capybara-3B-V1.9
Nous · duyntnet
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
NO
Nous Hermes 2 SOLAR 10.7B
Nous · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
Tool use
NO
Nous-Hermes-2-SOLAR-10.7B
Nous · duyntnet
Params10.7B
Context4K
Q4_K_M6.5 GB
Tool use
NO
Nous-Capybara-3B-V1.9
Nous · afrideva
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
NO
Nous Hermes 2 SOLAR 10.7B iMat
Nous · qwp4w3hyb
Params10.7B
Context4K
Q4_K_M6.5 GB
Tool use
NO
Nous Hermes 2 SOLAR 10.7B
Nous · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
Tool use
NO
Nous Capybara 7B V1.9 i1
Nous · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NO
Nous Capybara 7B V1.9
Nous · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NO
Nous Hermes ReflexAgent 8B v1
Nous · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
NO
Nous Hermes 2 MoE 2x34B i1
Nous · mradermacher
Params60.8B
Context4K
Q4_K_M36.7 GB
Tool use
NO
models--mergekit-community--Topsecret
Nous · MaziyarPanahi
Params4.62B
Context32K
Q4_K_M2.8 GB
Tool use
NO
franken SOLAR 18B v1.0
Nous · vicgalle
Params17.9B
Context4K
Smallest6.6 GB
Tool use

About the Nous GGUF models

Nous is represented on ggufmodels.com by 71 GGUF models, quantized by 30 uploaders on Hugging Face. The most downloaded are nousresearch_nous-capybara-34b, Nous Puffin 70B and nousresearch_nous-capybara-7b-v1.9. Parameter counts run from 1.64B to 69B, and the longest trained context window is 195K tokens.

A Q4_K_M file of a Nous model is between 1.7 to 41.4 GB, which is the quant most people start with. Most files come from mradermacher (18), TheBloke (9) and tensorblock (8). The quants you will meet most often are Q4_K_M (51), Q2_K (51), Q5_K_M (49) and Q6_K (44), where the number is how many models offer that quant.

Frequently asked questions

Which Nous GGUF should I download?

The most downloaded Nous GGUF here is nousresearch_nous-capybara-34b. 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 Nous model need?

Q4_K_M files of Nous models on this site range from 1.7 to 41.4 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 Nous GGUF files come from?

The most common quantizers here are mradermacher, TheBloke 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