GGUF models by afrideva

183 GGUF models quantized by afrideva on Hugging Face. Sizes run from 2M to 8.83B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
TI
Tinystories-gpt-0.1-3m
Tinystories · afrideva
Params7M
Context2K
Q4_K_M0.0 GB
GGUF
TI
TinyMistral 248M
Tinymistral · afrideva
Params248M
Context32K
Q4_K_M0.2 GB
GGUF
LO
LocutusqueXFelladrin TinyMistral248M Instruct
Locutusquexfelladrin · afrideva
Params248M
Context32K
Q4_K_M0.2 GB
GGUF
LL
Mermaid-Llama-6.7B-RAG-Code-Instruct
Llama · afrideva
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
TI
TinyLlama 1.1B Chat v0.5
Tinyllama · afrideva
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
TE
TeenyTinyLlama 460m Chat
Teenytinyllama · afrideva
Params468M
Context2K
Q4_K_M0.3 GB
GGUF
TI
Tiny Vicuna 1B
Tiny · afrideva
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
TI
TinyLlama 1.1B Chat v0.6
Tinyllama · afrideva
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
MI
japanese mistral 300m base
Mistral · afrideva
Params355M
Context4K
Q4_K_M0.2 GB
GGUF
PH
phi 2 dolly instruction polish
Phi · afrideva
Params2.78B
Context2K
Q4_K_M1.8 GB
GGUF
TI
TinyLlama 1.1B intermediate step 715k 1.5T airoboros 3.1 instruct V3
Tinyllama · afrideva
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
GP
gpt2-small-danish
Gpt · afrideva
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
TI
TinyLlama con brainstorming v0.2
Tinyllama · afrideva
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
TI
TinyLlama 1.1B Chat v0.4
Tinyllama · afrideva
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
PH
LMCocktail phi 2 v1
Phi · afrideva
Params2.78B
Context2K
Q4_K_M1.8 GB
GGUF
PH
phi 3 portuguese tom cat 4k instruct
Phi · afrideva
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
KA
kappa 3 phi abliterated
Kappa · afrideva
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
MI
malaysian mistral 1.1B 4096
Mistral · afrideva
Params1.12B
Context32K
Q4_K_M0.7 GB
GGUF
NO
Nous-Capybara-3B-V1.9
Nous · afrideva
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
TI
TinyLlama 1.1B intermediate step 955k token 2T
Tinyllama · afrideva
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
ZE
zephyr 220m dpo full
Zephyr · afrideva
Params218M
Context2K
Q4_K_M0.1 GB
GGUF
TI
TinyLlama haiku dpo v.0.1
Tinyllama · afrideva
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
ZE
Zephyr-3.43B
Zephyr · afrideva
Params3.43B
Context4K
Q4_K_M2.1 GB
GGUF
PH
Phi 3 mini 4k grammar correction
Phi · afrideva
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
ST
stablelm-2-1_6b
Stablelm · afrideva
Params1.64B
Context4K
Q4_K_M1.0 GB
Coding
ZE
zephyr 220m sft full
Zephyr · afrideva
Params218M
Context2K
Q4_K_M0.1 GB
GGUF
SM
SmolLlamix 8x101M
Smolllamix · afrideva
Params399M
Context32K
Q4_K_M0.2 GB
GGUF
MI
Hermes Trismegistus Mistral 7B
Mistral · afrideva
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
PH
phi 2 uncensored
Phi · afrideva
Params2.78B
Context2K
Q4_K_M1.8 GB
GGUF
DI
DialoGPT-medium-Oshiwambo-Bot
Dialogpt · afrideva
Params163M
Context1K
Q4_K_M0.1 GB
GGUF

About afrideva on Hugging Face

afrideva has published 183 GGUF models that ggufmodels.com tracks, across families such as Llama, Tinyllama and Phi. The most downloaded are Tinystories-gpt-0.1-3m, TinyMistral 248M and LocutusqueXFelladrin TinyMistral248M Instruct.

The quants afrideva publishes most often are Q6_K (183), Q5_K_M (183), Q4_K_M (183) and Q2_K (183). Their Q4_K_M files range from 0.0 to 5.3 GB. Parameter counts run from 2M to 8.83B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has afrideva published?

183 models are listed here, mainly from the Llama, Tinyllama and Phi families. The most downloaded is Tinystories-gpt-0.1-3m.

Which quants does afrideva publish?

The most common are Q6_K (183 models), Q5_K_M (183 models), Q4_K_M (183 models) and Q2_K (183 models).

Keep browsing