GGUF models by NexesQuants

283 GGUF models quantized by NexesQuants on Hugging Face. Sizes run from 488M to 141B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
WI
WinterGoddess 1.4x limarpv3 70B L2 32k Requant
Wintergoddess · NexesQuants
Params69B
Context32K
Smallest14.5 GB
GGUF
LL
Dolphin3.0 Llama3.1 1B abliterated
Llama · NexesQuants
Params1.24B
Context128K
Smallest0.9 GB
GGUF
SE
senku-70b
Senku · NexesQuants
Params69B
Context32K
Smallest14.1 GB
GGUF
LL
Llama 3.3 Nemotron 70B Instruct Abliterated TA v0.10 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest42.2 GB
Tool use
AL
alchemonaut QuartetAnemoi 70B iMat
Alchemonaut · NexesQuants
Params69B
Context32K
Smallest14.1 GB
GGUF
LL
Llama 3.1 Storm 8B
Llama · NexesQuants
Params8.03B
Context128K
Smallest3.7 GB
GGUF
VI
vigogne 33b instruct
Vigogne · NexesQuants
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
LL
calme-2.3-llama3.1-70b
Llama · NexesQuants
Params70.6B
Context128K
Smallest34.8 GB
GGUF
DE
DeepSeek R1 Distill Llama 70B Abliterated
DeepSeek · NexesQuants
Params70.6B
Context128K
Smallest48.1 GB
ReasoningTool use
MI
mistral small 3.1 24b instruct 2503 iMat IKLQ
Mistral · NexesQuants
Params23.6B
Context32K
Smallest7.2 GB
GGUF
LL
Tarek07 Legion V2.1 LLaMa 70B iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest20.2 GB
GGUF
LL
Huihui ai_Llama 3.3 70B Instruct Abliterated
Llama · NexesQuants
Params70.6B
Context128K
Smallest48.1 GB
Tool use
DO
Doctor Shotgun_L3.3 70B Magnum v4 SE
Doctor · NexesQuants
Params70.6B
Context128K
Smallest48.1 GB
Tool use
LL
llama 3 70B Instruct abliterated CQ
Llama · NexesQuants
Params70.6B
Context8K
Smallest32.7 GB
GGUF
AL
alicecomfy miqu 70b openhermes full iMat
Alicecomfy · NexesQuants
Params69B
Context32K
Smallest14.5 GB
Tool use
GE
Google_Gemma 3 27b It Qat Q4_0 Unquantized
Gemma · NexesQuants
Params27B
Context128K
Smallest14.8 GB
GGUF
UN
Undi95 Miqu 70B Alpaca DPO iMat
Undi · NexesQuants
Params69B
Context32K
Smallest18.3 GB
GGUF
LL
Llama 3.2 3b Kermes v2.1 iMat CQ
Llama · NexesQuants
Params3.21B
Context128K
Smallest1.3 GB
GGUF
LL
Llama 3.x 70b Nemotron L3.3 abliterated fusion v2 Mat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
Tool use
LA
lama 3.3 Tess 3 70B TA v0.60 iMat CQ
Lama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
GGUF
GL
Zai org_GLM 4.5 Air
GLM · NexesQuants
Params110B
Context128K
Smallest54.9 GB
GGUF
LL
Llama 3.x 70b L3.3 Nemotron abliterated fusion iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
Tool use
AL
alpindale WizardLM 2 8x22B bf16 iMat CQ
Alpindale · NexesQuants
Params141B
Context64K
Smallest60.5 GB
GGUF
WR
gghfez Writer Large 2411 iMat IKL CQ
Writer · NexesQuants
Params123B
Context128K
Smallest44.9 GB
GGUF
DE
DeepSeek V2 Lite Chat Uncensored Unbiased Reasoner
DeepSeek · NexesQuants
Params15.7B
Context4K
Smallest16.7 GB
Reasoning
NE
NeverSleep MiquMaid v2 70B DPO iMat
Neversleep · NexesQuants
Params69B
Context32K
Smallest14.5 GB
GGUF
LL
Meta Llama 3 70B Instruct
Llama · NexesQuants
Params70.6B
Context8K
Smallest31.6 GB
GGUF
CH
ChuckMcSneed WinterGoddess 1.4x 70b 32k iMat
Chuckmcsneed · NexesQuants
Params69B
Context32K
Smallest14.5 GB
GGUF
LL
Llama 3.x 70b Tristar V1.0 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
Tool use
LL
Llama 3.x 70b Trojka V3.8 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
Tool use

About NexesQuants on Hugging Face

NexesQuants has published 283 GGUF models that ggufmodels.com tracks, across families such as Llama, Gemma and Thedrummer. The most downloaded are WinterGoddess 1.4x limarpv3 70B L2 32k Requant, Dolphin3.0 Llama3.1 1B abliterated and senku-70b.

The quants NexesQuants publishes most often are Q8_0 (222), Q5_0 (191), BF16 (56) and Q3_K_M (13). Their Q4_K_M files range from 19.6 to 19.6 GB. Parameter counts run from 488M to 141B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has NexesQuants published?

283 models are listed here, mainly from the Llama, Gemma and Thedrummer families. The most downloaded is WinterGoddess 1.4x limarpv3 70B L2 32k Requant.

Which quants does NexesQuants publish?

The most common are Q8_0 (222 models), Q5_0 (191 models), BF16 (56 models) and Q3_K_M (13 models).

Keep browsing