GGUF models by elliotthwang

43 GGUF models quantized by elliotthwang on Hugging Face. Sizes run from 12M to 8.03B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
KimLan zh LLaMa GPTQ
Llama · elliotthwang
Params6.74B
Context2K
Smallest4.8 GB
GGUF
LL
KimLan zh LLaMa GPTQ V1.0
Llama · elliotthwang
Params6.74B
Context2K
Smallest4.1 GB
GGUF
GE
KimLan gemma2
Gemma · elliotthwang
Params2.61B
Context8K
Smallest1.7 GB
GGUF
PH
KimLanpure phi 3 zh
Phi · elliotthwang
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
PH
KimLan QA phi 2 zh
Phi · elliotthwang
Params2.78B
Context2K
Q4_K_M1.7 GB
GGUF
PH
KimLan phi 2 zh
Phi · elliotthwang
Params2.78B
Context2K
Q4_K_M1.8 GB
GGUF
PH
KimLam phi 2 zh
Phi · elliotthwang
Params2.78B
Context2K
Q4_K_M1.7 GB
GGUF
KI
KimLan 3.2 3B
Kimlan · elliotthwang
Params3.21B
Context128K
Smallest2.0 GB
Tool use
GE
Gemma 2b
Gemma · elliotthwang
Params2.51B
Context8K
Smallest1.6 GB
GGUF
LL
kimlanQA llama3.1 8b
Llama · elliotthwang
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
PH
KimLanpuretext phi 2 zh
Phi · elliotthwang
Params2.78B
Context2K
Q4_K_M1.7 GB
GGUF
LL
elliott Llama 2 7b zh
Llama · elliotthwang
Params6.74B
Context2K
Smallest4.1 GB
GGUF
LL
TW Llama 3.1 8B
Llama · elliotthwang
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
MI
KimLan mistral
Mistral · elliotthwang
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama 3.1 8B
Llama · elliotthwang
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MI
KimLam Mistral 7B v0.1 U
Mistral · elliotthwang
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
KimLan mistral 0.5b 40k
Mistral · elliotthwang
Params588M
Context40K
Smallest0.4 GB
GGUF
GE
KimLanpure gemma
Gemma · elliotthwang
Params2.51B
Context8K
Smallest1.6 GB
GGUF
LL
KimLan zh LLaMaU
Llama · elliotthwang
Params6.74B
Context2K
Smallest4.1 GB
GGUF
GE
Kimlanqacsv Gemma 2 2b It Tw
Gemma · elliotthwang
Params2.61B
Context8K
Smallest1.7 GB
GGUF
LL
elliott Llama 2 7b
Llama · elliotthwang
Params6.74B
Context4K
Smallest4.1 GB
GGUF
MI
KimLan mistral 3.2 3B
Mistral · elliotthwang
Params3.21B
Context128K
Smallest2.0 GB
Tool use
LL
KimLan zh LLaMa
Llama · elliotthwang
Params6.74B
Context2K
Smallest4.1 GB
GGUF
PH
KimLanpure phi 2 zh
Phi · elliotthwang
Params2.78B
Context2K
Q4_K_M1.7 GB
GGUF
KI
Kimlam Lama2 Chat Tw
Kimlam · elliotthwang
Params6.74B
Context4K
Smallest4.1 GB
GGUF
LL
DPO Kimlan Llama 2 7b Hf Tw
Llama · elliotthwang
Params6.74B
Context4K
Smallest4.1 GB
GGUF
GE
DPO Kimlan Gemma 2 2b It Tw
Gemma · elliotthwang
Params2.61B
Context8K
Smallest1.7 GB
GGUF
GE
DPO Kimlan Gemma 3 270M It Tw
Gemma · elliotthwang
Params268M
Context32K
Smallest0.3 GB
GGUF
SM
SmolLM 135M Instruct
SmolLM · elliotthwang
Params135M
Context2K
Smallest0.1 GB
GGUF
PH
Kimlan Phi 4 Mini Instruct Tw
Phi · elliotthwang
Params3.84B
Context128K
Smallest4.1 GB
GGUF

About elliotthwang on Hugging Face

elliotthwang has published 43 GGUF models that ggufmodels.com tracks, across families such as Llama, Phi and Mistral. The most downloaded are KimLan zh LLaMa GPTQ, KimLan zh LLaMa GPTQ V1.0 and KimLan gemma2.

The quants elliotthwang publishes most often are Q4_K_M (11), Q8_0 (9), Q5_K_M (9) and F16 (2). Their Q4_K_M files range from 1.7 to 4.9 GB. Parameter counts run from 12M to 8.03B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has elliotthwang published?

43 models are listed here, mainly from the Llama, Phi and Mistral families. The most downloaded is KimLan zh LLaMa GPTQ.

Which quants does elliotthwang publish?

The most common are Q4_K_M (11 models), Q8_0 (9 models), Q5_K_M (9 models) and F16 (2 models).

Keep browsing