GGUF models by Ffftdtd5dtft

35 GGUF models quantized by Ffftdtd5dtft on Hugging Face. Sizes run from 494M to 72.7B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
PH
Phi 3 Mini 128k Instruct
Phi · Ffftdtd5dtft
Params3.82B
Context128K
Smallest3.1 GB
Coding
MI
MiniCPM 2B sft bf16 Q2 K
MiniCPM · Ffftdtd5dtft
Params2.72B
Context4K
Smallest1.2 GB
GGUF
TI
TinyLlama 1.1B Chat v1.0
Tinyllama · Ffftdtd5dtft
Params1.1B
Context2K
Smallest0.3 GB
Coding
LL
Hermes 3 Llama 3.1 8B
Llama · Ffftdtd5dtft
Params8.03B
Context128K
Smallest2.0 GB
RoleplayTool use
GE
Gemma 2 9b It
Gemma · Ffftdtd5dtft
Params9.24B
Context8K
Smallest3.8 GB
GGUF
PH
Phi 3 Mini 128k Instruct
Phi · Ffftdtd5dtft
Params3.82B
Context128K
Smallest1.4 GB
Coding
WI
WizardLM 7B Uncensored
Wizardlm · Ffftdtd5dtft
Params6.74B
Context2K
Smallest2.5 GB
GGUF
QW
Qwen2 Math 72B Instruct
Qwen · Ffftdtd5dtft
Params72.7B
Context4K
Smallest29.8 GB
GGUF
QW
Qwen2 7B Instruct
Qwen · Ffftdtd5dtft
Params7.62B
Context32K
Smallest3.0 GB
GGUF
LL
Meta Llama 3.1 8B Instruct
Llama · Ffftdtd5dtft
Params8.03B
Context128K
Smallest3.2 GB
Tool use
DE
DeepSeek Coder V2 Lite Instruct
DeepSeek · Ffftdtd5dtft
Params15.7B
Context160K
Smallest6.4 GB
Coding
ST
Starcoder2 15b
StarCoder · Ffftdtd5dtft
Params16B
Context16K
Smallest6.2 GB
Coding
QW
Qwen2 0.5B
Qwen · Ffftdtd5dtft
Params494M
Context128K
Smallest0.3 GB
GGUF
LL
Meta Llama 3.1 8B
Llama · Ffftdtd5dtft
Params8.03B
Context128K
Smallest3.2 GB
GGUF
MI
Codestral 22B v0.1
Mistral · Ffftdtd5dtft
Params22.2B
Context32K
Smallest8.3 GB
Coding
LL
Meta Llama 3.1 70B Instruct
Llama · Ffftdtd5dtft
Params70.6B
Context128K
Smallest26.4 GB
Tool use
GE
Gemma 2 2b
Gemma · Ffftdtd5dtft
Params2.61B
Context8K
Smallest0.8 GB
GGUF
ST
Starcoder2 3b
StarCoder · Ffftdtd5dtft
Params3.03B
Context16K
Smallest1.2 GB
Coding
WI
WizardLM 13B Uncensored
Wizardlm · Ffftdtd5dtft
Params13B
Context2K
Smallest4.9 GB
GGUF
QW
Qwen2 Math 7B Instruct
Qwen · Ffftdtd5dtft
Params7.62B
Context4K
Smallest3.0 GB
GGUF
LL
Meta Llama 3.1 70B
Llama · Ffftdtd5dtft
Params70.6B
Context128K
Smallest26.4 GB
GGUF
GE
Gemma 2 2b It
Gemma · Ffftdtd5dtft
Params2.61B
Context8K
Smallest0.8 GB
GGUF
GE
Gemma 2 2b It
Gemma · Ffftdtd5dtft
Params2.61B
Context8K
Smallest1.2 GB
GGUF
LL
Luna AI Llama2 Uncensored Q2 K
Llama · Ffftdtd5dtft
Params6.74B
Context2K
Smallest2.5 GB
GGUF
QW
Qwen2 0.5B Instruct
Qwen · Ffftdtd5dtft
Params494M
Context32K
Smallest0.3 GB
GGUF
GP
Gpt2 Xl
Gpt · Ffftdtd5dtft
Params1.64B
Context1K
Smallest0.9 GB
GGUF
SH
Shieldgemma 2b
Shieldgemma · Ffftdtd5dtft
Params2.61B
Context8K
Smallest1.2 GB
GGUF
GE
Gemma 2 27b
Gemma · Ffftdtd5dtft
Params27.2B
Context8K
Smallest10.4 GB
GGUF
PH
Phi 3.5 Mini Instruct
Phi · Ffftdtd5dtft
Params3.82B
Context128K
Smallest1.4 GB
Coding
MI
Mistral NeMo Minitron 8B Base
Mistral · Ffftdtd5dtft
Params8.41B
Context8K
Smallest2.1 GB
GGUF

About Ffftdtd5dtft on Hugging Face

Ffftdtd5dtft has published 35 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Gemma. The most downloaded are Phi 3 Mini 128k Instruct, MiniCPM 2B sft bf16 Q2 K and TinyLlama 1.1B Chat v1.0.

The quants Ffftdtd5dtft publishes most often are Q2_K (25), IQ1_S (8), IQ2_XXS (1) and BF16 (1). Parameter counts run from 494M to 72.7B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has Ffftdtd5dtft published?

35 models are listed here, mainly from the Qwen, Llama and Gemma families. The most downloaded is Phi 3 Mini 128k Instruct.

Which quants does Ffftdtd5dtft publish?

The most common are Q2_K (25 models), IQ1_S (8 models), IQ2_XXS (1 models) and BF16 (1 models).

Keep browsing