GGUF models by Ak1104

35 GGUF models quantized by Ak1104 on Hugging Face. Sizes run from 6.74B to 22.2B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
codellama 7b rust
Llama · Ak1104
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
WI
QA_withoutChapter
Withoutchapter · Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
codellama_cde
Llama · Ak1104
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
MI
Codestral 22B v0.1
Mistral · Ak1104
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
CD
cde 3.1 3
Cde · Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
codellama_4k_7b_PT
Llama · Ak1104
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
CD
pt cde
Cde · Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
CO
combined 3.1
Combined · Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
llama 3 test
Llama · Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
combined dataset rust
Llama · Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
CD
cde 3.1 4 instruct
Cde · Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
WI
QA_2k_withoutChapter
Withoutchapter · Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
3 70B
Llama · Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
NO
31 noPT 2k
Nopt · Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
31
3.1 2
Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MO
my_models
Models · Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
CO
3.1 combined noPT
Combined · Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
RU
Rust_Code_Explanation_Final
Rust · Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
Coding
MO
QA_model
Model · Ak1104
Params8.03B
Context256K
Q4_K_M4.9 GB
GGUF
LL
Meta Llama 3.1 8B
Llama · Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
QA
QA pt
Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
TE
3 test q8
Test · Ak1104
Params8.03B
Context8K
Smallest8.5 GB
GGUF
LL
3n
Llama · Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
3T
3T
Ak1104
Params8.03B
Context8K
Smallest4.9 GB
GGUF
WI
QA2_withoutChapter
Withoutchapter · Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
QA
QA 2k
Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
OB
Obj1
Obj · Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
CO
combined 3.1 2
Combined · Ak1104
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
CD
pt_cde_4k
Cde · Ak1104
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
PR
prompt1
Prompt · Ak1104
Params8.03B
Context8K
Smallest16.1 GB
GGUF

About Ak1104 on Hugging Face

Ak1104 has published 35 GGUF models that ggufmodels.com tracks, across families such as Llama, Cde and Withoutchapter. The most downloaded are codellama 7b rust, QA_withoutChapter and codellama_cde.

The quants Ak1104 publishes most often are Q4_K_M (31), F16 (24), Q8_0 (2) and Q5_K_M (1). Their Q4_K_M files range from 4.1 to 13.3 GB. Parameter counts run from 6.74B to 22.2B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has Ak1104 published?

35 models are listed here, mainly from the Llama, Cde and Withoutchapter families. The most downloaded is codellama 7b rust.

Which quants does Ak1104 publish?

The most common are Q4_K_M (31 models), F16 (24 models), Q8_0 (2 models) and Q5_K_M (1 models).

Keep browsing