GGUF models by Ramikan-BR

77 GGUF models quantized by Ramikan-BR on Hugging Face. Sizes run from 494M to 8.03B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
TI
tinyllama-coder-py-4bit-v10
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
QW
Qwen2 0.5B v22
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
TI
tinyllama-coder-py-v12
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
TI
tinyllama-coder-py-v16
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
TI
TiamaPY-v31
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
GGUF
TI
TiamaPY-v32
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
GGUF
TI
tinyllama-coder-py-v15
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
TI
tinyllama-coder-py-v11
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
TI
tinyllama-coder-py-4bit-v9
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
TI
tinyllama-coder-py-4bit-v8
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
TI
TiamaPY-v34
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
GGUF
TI
tinyllama-coder-py-v21
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
TI
tinyllama-coder-py-v18
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
TI
tinyllama-coder-py-v20
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
QW
Qwen2 0.5B v32
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
QW
Qwen2 0.5B v26
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
QW
Qwen2-0.5B-v3
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
TI
TiamaPY-v33
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Smallest1.2 GB
GGUF
QW
Qwen2 0.5B v23
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
QW
Qwen2 0.5B v17
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
QW
Qwen2 0.5B v16
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
QW
Qwen2 0.5B v28
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
TI
tinyllama-coder-py-v13
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding
QW
Qwen2 0.5B v31
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
QW
Qwen2 0.5B v21
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
QW
Qwen2 0.5B v25
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
QW
Qwen2 0.5B v27
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
QW
Qwen2 0.5B v10
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
QW
Qwen2-0.5B-v4
Qwen · Ramikan-BR
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
TI
tinyllama-coder-py-4bit-v7
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
Coding

About Ramikan-BR on Hugging Face

Ramikan-BR has published 77 GGUF models that ggufmodels.com tracks, across families such as Tinyllama, Qwen and Mini. The most downloaded are tinyllama-coder-py-4bit-v10, Qwen2 0.5B v22 and tinyllama-coder-py-v12.

The quants Ramikan-BR publishes most often are F16 (58), Q8_0 (45) and Q4_K_M (44). Their Q4_K_M files range from 0.4 to 4.9 GB. Parameter counts run from 494M to 8.03B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has Ramikan-BR published?

77 models are listed here, mainly from the Tinyllama, Qwen and Mini families. The most downloaded is tinyllama-coder-py-4bit-v10.

Which quants does Ramikan-BR publish?

The most common are F16 (58 models), Q8_0 (45 models) and Q4_K_M (44 models).

Keep browsing