GGUF models by NeverSleep

40 GGUF models quantized by NeverSleep on Hugging Face. Sizes run from 7.24B to 125B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
LU
Lumimaid v0.2 12B
Lumimaid · NeverSleep
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
LU
Lumimaid v0.2 8B
Lumimaid · NeverSleep
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MI
Noromaid-v0.1-mixtral-8x7b
Mistral · NeverSleep
Params46.7B
Context32K
Q4_K_M26.4 GB
GGUF
MI
Noromaid v0.4 Mixtral Instruct 8x7b Zloss
Mistral · NeverSleep
Params46.7B
Context32K
Q4_K_M26.4 GB
GGUF
LL
NeverSleep_Llama-3-Lumimaid-8B-v0.1
Llama · NeverSleep
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 Lumimaid 8B v0.1 OAS
Llama · NeverSleep
Params8.03B
Context8K
Smallest4.7 GB
GGUF
MI
Noromaid-v0.1-mixtral-8x7b-Instruct-v3
Mistral · NeverSleep
Params46.7B
Context32K
Q4_K_M26.4 GB
GGUF
FL
FlatOrcamaid 13b v0.2
Flatorcamaid · NeverSleep
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
NO
Noromaid 13b v0.3
Noromaid · NeverSleep
Params13B
Context4K
Smallest7.4 GB
GGUF
NE
Nethena 13B
Nethena · NeverSleep
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
NO
Noromaid 13b v0.1.1
Noromaid · NeverSleep
Params13B
Context4K
Smallest7.4 GB
GGUF
EC
Echidna 13b v0.3
Echidna · NeverSleep
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
NO
Noromaid 13B 0.4 DPO
Noromaid · NeverSleep
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
EC
Echidna 13b v0.2
Echidna · NeverSleep
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
NO
Noromaid 7B 0.4 DPO
Noromaid · NeverSleep
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NO
Noromaid 13b v0.2
Noromaid · NeverSleep
Params13B
Context4K
Smallest7.4 GB
GGUF
NO
Noromaid 7b v0.1.1
Noromaid · NeverSleep
Params7.24B
Context32K
Smallest5.1 GB
GGUF
LU
Lumimaid v0.2 70B
Lumimaid · NeverSleep
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
NE
Nethena 20B
Nethena · NeverSleep
Params20B
Context4K
Smallest8.7 GB
GGUF
EC
Echidna 13b v0.1
Echidna · NeverSleep
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
NO
Noromaid 20b v0.1.1
Noromaid · NeverSleep
Params20B
Context4K
Smallest9.7 GB
GGUF
CA
CausalLM RP 34B
Causallm · NeverSleep
Params34.4B
Context195K
Q4_K_M20.7 GB
Roleplay
MI
MiquMaid v2 2x70B DPO
Miqumaid · NeverSleep
Params125B
Context32K
Smallest33.0 GB
GGUF
HO
HornyEchidna 13b v0.1
Hornyechidna · NeverSleep
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
MI
NoromaidxOpenGPT4 2 GGUF iMatrix
Mistral · NeverSleep
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
NO
X NoroChronos 13B
Norochronos · NeverSleep
Params13B
Context4K
Smallest7.4 GB
GGUF
MI
Mistral 11B SynthIAirOmniMix
Mistral · NeverSleep
Params10.7B
Context32K
Q4_K_M6.5 GB
GGUF
MI
Mistral 11B AirOmniMix
Mistral · NeverSleep
Params10.7B
Context32K
Smallest8.8 GB
GGUF
NO
Noromaid 7b v0.2
Noromaid · NeverSleep
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
NeverSleep_Llama-3-Lumimaid-70B-v0.1
Llama · NeverSleep
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF

About NeverSleep on Hugging Face

NeverSleep has published 40 GGUF models that ggufmodels.com tracks, across families such as Noromaid, Mistral and Miqumaid. The most downloaded are Lumimaid v0.2 12B, Lumimaid v0.2 8B and Noromaid-v0.1-mixtral-8x7b.

The quants NeverSleep publishes most often are Q5_K_M (35), Q8_0 (29), Q4_K_M (28) and Q6_K (27). Their Q4_K_M files range from 4.4 to 42.5 GB. Parameter counts run from 7.24B to 125B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has NeverSleep published?

40 models are listed here, mainly from the Noromaid, Mistral and Miqumaid families. The most downloaded is Lumimaid v0.2 12B.

Which quants does NeverSleep publish?

The most common are Q5_K_M (35 models), Q8_0 (29 models), Q4_K_M (28 models) and Q6_K (27 models).

Keep browsing