GGUF models by RichardErkhov

14354 GGUF models quantized by RichardErkhov on Hugging Face. Sizes run from 1M to 316B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
TO
Topxtral-4x7B-v0.1
Topxtral · RichardErkhov
Params18.5B
Context32K
Q4_K_M11.2 GB
GGUF
SE
SeaLLMs SeaLLMs v3 7B Chat
Seallms · RichardErkhov
Params7.62B
Context—
Q4_K_M0.0 GB
GGUF
FA
Jiqing tiny random falcon
Falcon · RichardErkhov
Params—
Context—
Q4_K_M0.0 GB
GGUF
GR
ibm granite granite 20b code instruct
Granite · RichardErkhov
Params1.9B
Context—
Q4_K_M0.0 GB
Coding
AN
anthracite org magnum 12b v2
Anthracite · RichardErkhov
Params12.2B
Context—
Q4_K_M0.0 GB
GGUF
GR
ibm granite granite 20b code base
Granite · RichardErkhov
Params1.9B
Context—
Q4_K_M0.0 GB
Coding
QW
Qwen2 1.5B Instruct
Qwen · RichardErkhov
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
BE
BeaverAI NeMoist 21B v1a
Beaverai · RichardErkhov
Params21B
Context—
Q4_K_M0.0 GB
GGUF
FB
fblgit juanako 7b UNA
Fblgit · RichardErkhov
Params7.24B
Context—
Q4_K_M0.0 GB
GGUF
SA
Sao10K L3 8B Stheno v3.1
Sao · RichardErkhov
Params8B
Context—
Q4_K_M0.3 GB
GGUF
MI
avemio digital mistral 7b Sft pretrain 6000 steps merge
Mistral · RichardErkhov
Params7.24B
Context—
Q4_K_M0.1 GB
GGUF
LL
testmod koen llama2 13b dpotrain testver
Llama · RichardErkhov
Params13B
Context—
Q4_K_M0.0 GB
GGUF
BA
BarryFutureman NeuralTurdusVariant1 7B
Barryfutureman · RichardErkhov
Params7B
Context—
Q4_K_M0.0 GB
GGUF
LL
VAGOsolutions Llama 3 SauerkrautLM 70b Instruct
Llama · RichardErkhov
Params6B
Context—
Q4_K_M0.0 GB
GGUF
UN
Undi95 Emerhyst 20B
Undi · RichardErkhov
Params920M
Context—
Q4_K_M0.0 GB
GGUF
LL
4yo1 llama3 pre1 pre2 ds ins2 lora3
Llama · RichardErkhov
Params200M
Context—
Q4_K_M0.0 GB
GGUF
GE
avemio digital gemma 2b Sft pretrain 6000 steps merge
Gemma · RichardErkhov
Params2.5B
Context8K
Q4_K_M1.6 GB
GGUF
PH
gretelai Phi 3 mini 128k instruct
Phi · RichardErkhov
Params1.9B
Context—
Q4_K_M0.0 GB
GGUF
LL
tachyphylaxis Meta Llama 3.1 Chat Uncensored
Llama · RichardErkhov
Params15M
Context—
Q4_K_M0.0 GB
GGUF
LL
KISTI KONI KONI Llama3 8B Instruct 20240729
Llama · RichardErkhov
Params8B
Context—
Q4_K_M0.0 GB
GGUF
CO
Yi Coder 9B Chat
Coder · RichardErkhov
Params8.83B
Context128K
Q4_K_M5.3 GB
Coding
MI
maywell Mistral ko 7B v0.1
Mistral · RichardErkhov
Params1.5B
Context—
Q4_K_M0.0 GB
GGUF
CO
Yi Coder 9B
Coder · RichardErkhov
Params8.83B
Context128K
Q4_K_M5.3 GB
Coding
YI
Yi 6B Chat
Yi · RichardErkhov
Params6.06B
Context4K
Q4_K_M3.7 GB
GGUF
LL
turboderp Cat Llama 3 70B instruct
Llama · RichardErkhov
Params3.3B
Context—
Q4_K_M0.0 GB
GGUF
LL
FILM6912 Meta Llama 3.1 8B Instruct
Llama · RichardErkhov
Params8B
Context—
Q4_K_M0.0 GB
GGUF
HE
0 hero Matter 0.2 7B
Hero · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
YI
Yi 1.5 34B Chat
Yi · RichardErkhov
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
LL
4 alokk llama 3 8b English to Hinglish
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
CO
CohereForAI aya 23 35B
Cohereforai · RichardErkhov
Params35B
Context—
Q4_K_M0.0 GB
GGUF

About RichardErkhov on Hugging Face

RichardErkhov has published 14,354 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Mistral. The most downloaded are Topxtral-4x7B-v0.1, SeaLLMs SeaLLMs v3 7B Chat and Jiqing tiny random falcon.

The quants RichardErkhov publishes most often are Q2_K (14352), Q3_K_S (14059), Q3_K (13884) and Q3_K_M (13868). Their Q4_K_M files range from 0.0 to 129.1 GB. Parameter counts run from 1M to 316B, and the longest trained context window is 102400K tokens.

Frequently asked questions

What GGUF models has RichardErkhov published?

14,354 models are listed here, mainly from the Llama, Qwen and Mistral families. The most downloaded is Topxtral-4x7B-v0.1.

Which quants does RichardErkhov publish?

The most common are Q2_K (14352 models), Q3_K_S (14059 models), Q3_K (13884 models) and Q3_K_M (13868 models).

Keep browsing