GGUF models by Edge-Quant
79 GGUF models quantized by Edge-Quant on Hugging Face. Sizes run from 16M to 9.4B parameters. The longest trained context is 501K tokens.
JA
Jan v1 Edge
Jan · Edge-Quant
Params1.72B
Context40K
Q4_K_M1.1 GB
AQ
Aquif 3.5 Nano 1B
Aquif · Edge-Quant
Params1.72B
Context40K
Q4_K_M1.1 GB
LL
Llama 3.2 3B Instruct
Llama · Edge-Quant
Params3.21B
Context128K
Q4_K_M2.0 GB
IN
Internlm2 Chat 1_8b
InternLM · Edge-Quant
Params1.89B
Context32K
Q4_K_M1.2 GB
AQ
Aquif 3.6 8B
Aquif · Edge-Quant
Params8.19B
Context40K
Q4_K_M5.0 GB
LL
Llama 3.2 1B Instruct
Llama · Edge-Quant
Params1.24B
Context128K
Q4_K_M0.8 GB
HU
Huihui EXAONE 4.0 1.2B Abliterated
Huihui · Edge-Quant
Params1.28B
Context64K
Smallest0.9 GB
HI
Hito 1.7b
Hito · Edge-Quant
Params1.72B
Context40K
Q4_K_M1.1 GB
GE
Gemma 3 4b It
Gemma · Edge-Quant
Params3.88B
Context128K
Q4_K_M2.5 GB
SM
SmolLM3 3B
SmolLM · Edge-Quant
Params3.08B
Context64K
Q4_K_M1.9 GB
YU
YuLan Mini
Yulan · Edge-Quant
Params2.42B
Context28K
Q4_K_M1.8 GB
RE
ReaderLM v2 Q4 K M
Readerlm · Edge-Quant
Params1.54B
Context501K
Q4_K_M1.0 GB
GR
Granite 4.0 Micro
Granite · Edge-Quant
Params3.4B
Context128K
Q4_K_M2.1 GB
TR
Transcript Analytics SLM1.5b
Transcript · Edge-Quant
Params1.54B
Context32K
Q4_K_M1.0 GB
OP
Open0 2 Lite
Open · Edge-Quant
Params1.72B
Context40K
Q4_K_M1.1 GB
SM
SmallThinker 3B Preview
Smallthinker · Edge-Quant
Params3.4B
Context32K
Q4_K_M2.1 GB
LL
Llama 3.2 1B Instruct Hindi Q8 0
Llama · Edge-Quant
Params1.5B
Context128K
Smallest1.6 GB
AF
AFM 4.5B
Afm · Edge-Quant
Params4.62B
Context64K
Q4_K_M2.9 GB
BI
bigscience small finetune
Bigscience · Edge-Quant
Params16M
Context20
Smallest0.0 GB