GGUF models by Nexesenex

44 GGUF models quantized by Nexesenex on Hugging Face. Sizes run from 1.24B to 94.6B parameters. The longest trained context is 195K tokens.

Most downloadedNewestLargestLongest contextSmallest
YI
brucethemoose Yi 34B 200K DARE megamerge v8 iMat
Yi · Nexesenex
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
GE
Google_Gemma_2_9b_it
Gemma · Nexesenex
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
YI
brucethemoose Yi 34B 200K DARE merge v7 iMat
Yi · Nexesenex
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
LL
Codellama 2 7b Miniguanaco Mistral
Llama · Nexesenex
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
YI
abacusai Smaug Yi 34B v0.1 iMat
Yi · Nexesenex
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
LL
Llama 3.2 1b OpenTree R1 0.1
Llama · Nexesenex
Params1.5B
Context128K
Smallest0.6 GB
ReasoningTool use
BH
bhenrym14 airoboros 33b gpt4 1.4.1 lxctx PI 16384
Bhenrym · Nexesenex
Params32.5B
Context16K
Q4_K_M19.6 GB
GGUF
TO
TomGrc FusionNet 7Bx2 MoE v0.1 iMat
Tomgrc · Nexesenex
Params12.9B
Context32K
Smallest4.4 GB
GGUF
LL
Meta_Llama_3.1_8b_it
Llama · Nexesenex
Params8.03B
Context128K
Smallest2.9 GB
Tool use
MI
Airoboros c34b 2.2.1 Mistral
Mistral · Nexesenex
Params33.7B
Context16K
Q4_K_M20.2 GB
GGUF
AI
airoboros 33b gpt4 m2.0
Airoboros · Nexesenex
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
AI
airoboros 33b gpt4 2.0
Airoboros · Nexesenex
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
LL
Llama 3.2 3b KermesPink V3.6
Llama · Nexesenex
Params3.21B
Context128K
Smallest1.8 GB
GGUF
BH
bhenrym14 airophin v2 13b PI 8k iMat
Bhenrym · Nexesenex
Params13B
Context8K
Smallest3.5 GB
GGUF
LL
Llama-3.2-1B-Instruct-Open-R1-GRPO
Llama · Nexesenex
Params1.5B
Context128K
Smallest0.8 GB
ReasoningTool use
YI
bhenrym14 airoboros 3 1 yi 34b 200k iMat
Yi · Nexesenex
Params34.4B
Context195K
Smallest9.3 GB
GGUF
VI
vicuna 33b v1.3
Vicuna · Nexesenex
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
LL
Llama 3.2 1b RandomLego RP R1 0.1
Llama · Nexesenex
Params1.5B
Context128K
Smallest0.9 GB
ReasoningRoleplayTool use
TO
TomGrc FusionNet 34Bx2 MoE v0.1 iMat
Tomgrc · Nexesenex
Params60.8B
Context195K
Smallest20.8 GB
GGUF
LL
Llama 3.2 3b Shark 0.0
Llama · Nexesenex
Params3.21B
Context128K
Smallest2.6 GB
Tool use
ON
one man army UNA 34Beagles 32K v1 iMat
One · Nexesenex
Params34.4B
Context32K
Q4_K_M20.7 GB
GGUF
YI
brucethemoose Yi 34b Capybara 200K Fixed Temp iMat
Yi · Nexesenex
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
JO
jondurbin bagel 7b v0.4 iMat
Jondurbin · Nexesenex
Params7.24B
Context32K
Smallest2.2 GB
GGUF
MI
cloudyu Mixtral 7Bx2 MoE 13B iMat
Mistral · Nexesenex
Params12.9B
Context32K
Smallest13.7 GB
GGUF
LL
meditsolutions_Llama 3.2 SUN 1B Instruct
Llama · Nexesenex
Params1.5B
Context128K
Smallest1.6 GB
ReasoningTool use
LL
Llama 3.2 3b BlueKermes 0.39
Llama · Nexesenex
Params3.21B
Context128K
Smallest1.9 GB
GGUF
MI
cloudyu Mixtral 34Bx2 MoE 60B iMat
Mistral · Nexesenex
Params60.8B
Context195K
Smallest20.8 GB
GGUF
LL
Llama 3.2 3b KermesRed V3.4
Llama · Nexesenex
Params3.21B
Context128K
Smallest1.9 GB
GGUF
AI
airoboros c34b 2.2.1
Airoboros · Nexesenex
Params33.7B
Context16K
Q4_K_M20.2 GB
GGUF
YI
SanjiWatsuki SUS Wizard Yi 34B iMat
Yi · Nexesenex
Params34.4B
Context8K
Q4_K_M20.7 GB
GGUF

About Nexesenex on Hugging Face

Nexesenex has published 44 GGUF models that ggufmodels.com tracks, across families such as Llama, Yi and Mistral. The most downloaded are brucethemoose Yi 34B 200K DARE megamerge v8 iMat, Google_Gemma_2_9b_it and brucethemoose Yi 34B 200K DARE merge v7 iMat.

The quants Nexesenex publishes most often are Q8_0 (32), Q4_K_S (19), Q4_K_M (18) and Q3_K_M (17). Their Q4_K_M files range from 4.1 to 20.7 GB. Parameter counts run from 1.24B to 94.6B, and the longest trained context window is 195K tokens.

Frequently asked questions

What GGUF models has Nexesenex published?

44 models are listed here, mainly from the Llama, Yi and Mistral families. The most downloaded is brucethemoose Yi 34B 200K DARE megamerge v8 iMat.

Which quants does Nexesenex publish?

The most common are Q8_0 (32 models), Q4_K_S (19 models), Q4_K_M (18 models) and Q3_K_M (17 models).

Keep browsing