GGUF models by forkjoin-ai

53 GGUF models quantized by forkjoin-ai on Hugging Face. Sizes run from 362M to 72.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen2 Audio 7B Instruct
Qwen · forkjoin-ai
Params7.75B
Context8K
Q4_K_M4.8 GB
GGUF
LO
loki erotica 8b
Loki · forkjoin-ai
Params8.03B
Context1024K
Q4_K_M4.9 GB
GGUF
QW
qwen2.5-7b-instruct
Qwen · forkjoin-ai
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
UN
unlimited ocr
Unlimited · forkjoin-ai
Params2.93B
Context32K
Q4_K_M2.0 GB
GGUF
QW
buleyean qwen2.5 0.5b
Qwen · forkjoin-ai
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
LL
llama 3.1 nemotron nano vl 8b v1
Llama · forkjoin-ai
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool useVision
DE
DeepSeek-OCR
DeepSeek · forkjoin-ai
Params2.93B
Context—
Smallest2.1 GB
GGUF
QW
Qwen2.5 Coder 7B Instruct
Qwen · forkjoin-ai
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
QW
Qwen2.5 VL 3B Instruct
Qwen · forkjoin-ai
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
TI
tinyllama_tinyllama-1.1b-chat-v1.0
Tinyllama · forkjoin-ai
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
QW
qwen2.5-0.5b-instruct
Qwen · forkjoin-ai
Params630M
Context32K
Q4_K_M0.5 GB
Tool use
LL
Llama 3.3 70B Instruct
Llama · forkjoin-ai
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
SM
buleyean smollm2 360m
SmolLM · forkjoin-ai
Params362M
Context8K
Q4_K_M0.3 GB
GGUF
QW
Qwen3 8B Instruct
Qwen · forkjoin-ai
Params8.19B
Context40K
Smallest8.7 GB
ReasoningTool use
LL
Meta Llama 3.1 70B Instruct
Llama · forkjoin-ai
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
QW
Qwen3 4B Instruct
Qwen · forkjoin-ai
Params4.02B
Context40K
Smallest4.3 GB
ReasoningTool use
GL
glm ocr
GLM · forkjoin-ai
Params891M
Context128K
Smallest1.0 GB
Vision
LL
Llama 3.2 3B Instruct
Llama · forkjoin-ai
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LL
Meta-Llama-3-8B-Instruct
Llama · forkjoin-ai
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Gemma 3 4b It
Gemma · forkjoin-ai
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
LL
Meta Llama 3.1 8B Instruct
Llama · forkjoin-ai
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
PE
personaplex 7b
Personaplex · forkjoin-ai
Params8.37B
Context—
Smallest4.7 GB
GGUF
QW
Qwen3 VL 8B Instruct
Qwen · forkjoin-ai
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
QW
Qwen2.5 72B Instruct
Qwen · forkjoin-ai
Params72.7B
Context32K
Q4_K_M47.4 GB
Tool use
QW
Qwen3Vl 2b Instruct
Qwen · forkjoin-ai
Params1.72B
Context256K
Smallest1.8 GB
Tool useVision
QW
qwen2.5-1.5b-instruct
Qwen · forkjoin-ai
Params1.78B
Context32K
Q4_K_M1.1 GB
Tool use
LL
llama 2 70b chat
Llama · forkjoin-ai
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
QW
Qwen2.5 VL 7B Instruct
Qwen · forkjoin-ai
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
LL
Meta Llama 3.1 8B Instruct
Llama · forkjoin-ai
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
QW
Qwen3 VL 30B A3B Instruct
Qwen · forkjoin-ai
Params30.5B
Context256K
Q4_K_M18.6 GB
Tool useVision

About forkjoin-ai on Hugging Face

forkjoin-ai has published 53 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Gemma. The most downloaded are Qwen2 Audio 7B Instruct, loki erotica 8b and qwen2.5-7b-instruct.

The quants forkjoin-ai publishes most often are Q4_K_M (44), Q8_0 (9), Q4_K (2) and F16 (2). Their Q4_K_M files range from 0.3 to 47.4 GB. Parameter counts run from 362M to 72.7B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has forkjoin-ai published?

53 models are listed here, mainly from the Qwen, Llama and Gemma families. The most downloaded is Qwen2 Audio 7B Instruct.

Which quants does forkjoin-ai publish?

The most common are Q4_K_M (44 models), Q8_0 (9 models), Q4_K (2 models) and F16 (2 models).

Keep browsing