GGUF models by redponike
45 GGUF models quantized by redponike on Hugging Face. Sizes run from 1.72B to 229B parameters. The longest trained context is 256K tokens.
QW
Replete LLM V2.5 Qwen 7b
Qwen · redponike
Params7.62B
Context32K
Q4_K_M4.7 GB
GE
Gemma-2-9B-It-SPPO-Iter3
Gemma · redponike
Params9.24B
Context8K
Q4_K_M5.8 GB
AU
AutoCoder
Autocoder · redponike
Params33.3B
Context16K
Q4_K_M19.9 GB
LL
Llama-3-Instruct-8B-SPPO-Iter3
Llama · redponike
Params8.03B
Context8K
Q4_K_M4.9 GB
YI
Yi-1.5-34B-32K
Yi · redponike
Params34.4B
Context32K
Smallest15.0 GB
HU
Hunyuan A13B Instruct
Hunyuan · redponike
Params80.4B
Context256K
Q4_K_M48.8 GB
PH
phi 4
Phi · redponike
Params14.7B
Context16K
Smallest6.5 GB
LL
Llama-3-KafkaLM-8B-v0.1
Llama · redponike
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama-3-WhiteRabbitNeo-8B-v2.0
Llama · redponike
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Smaug-Llama-3-70B-Instruct
Llama · redponike
Params70.6B
Context8K
Smallest26.4 GB
KA
KafkaLM 15B
Kafkalm · redponike
Params15.6B
Context32K
Q4_K_M9.5 GB
LL
Llama-3-SauerkrautLM-70b-Instruct
Llama · redponike
Params70.6B
Context8K
Smallest26.4 GB
YI
Yi-1.5-9B-32K
Yi · redponike
Params8.83B
Context32K
Q4_K_M5.3 GB
MA
MAmmoTH2-8B-Plus
Mammoth · redponike
Params8.03B
Context8K
Q4_K_M4.9 GB
MA
MAmmoTH2-8x7B-Plus
Mammoth · redponike
Params46.7B
Context32K
Q4_K_M28.4 GB