GGUF models by ggml-org

224 GGUF models quantized by ggml-org on Hugging Face. Sizes run from 1M to 1050B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
LoRA Qwen2.5 Coder 7B Instruct
Qwen · ggml-org
Params182M
Context—
Smallest0.7 GB
GGUF
QW
LoRA Qwen2.5 32B Instruct Abliterated
Qwen · ggml-org
Params279M
Context—
Smallest1.1 GB
GGUF
QW
LoRA Qwen2.5 7B Instruct Abliterated v3
Qwen · ggml-org
Params91M
Context—
Smallest0.4 GB
GGUF
QW
Qwen3 30B A3B Thinking 2507
Qwen · ggml-org
Params30.5B
Context256K
Smallest32.5 GB
ReasoningTool use
LL
LoRA Llama 3 Instruct abliteration 8B F16
Llama · ggml-org
Params88M
Context—
Smallest0.4 GB
GGUF
GE
gemma-1.1-7b-it
Gemma · ggml-org
Params8.54B
Context8K
Smallest9.1 GB
GGUF
QW
LoRA Qwen2.5 14B Instruct Abliterated v2
Qwen · ggml-org
Params296M
Context—
Smallest1.2 GB
GGUF
LO
LoRA SmallThinker 3B Preview
Lora · ggml-org
Params140M
Context—
Smallest0.6 GB
GGUF
LO
LoRA Deepthink Reasoning 7B
Lora · ggml-org
Params182M
Context—
Smallest0.7 GB
GGUF
LL
LoRA Llama 3.1 8B MultiReflection
Llama · ggml-org
Params185M
Context—
Smallest0.7 GB
GGUF
GR
Granite 4.0 H Small
Granite · ggml-org
Params32.2B
Context1024K
Smallest34.3 GB
GGUF
QW
LoRA Human Like Qwen2.5 7B Instruct
Qwen · ggml-org
Params182M
Context—
Smallest0.7 GB
GGUF
QW
LoRA Qwerus Qwen2.5 7B Instruct F16
Qwen · ggml-org
Params91M
Context—
Smallest0.4 GB
GGUF
QW
Qwen3 Next 80B A3B Instruct
Qwen · ggml-org
Params79.7B
Context256K
Smallest84.8 GB
Tool use
GE
gemma-1.1-7b-it
Gemma · ggml-org
Params8.54B
Context8K
Smallest5.0 GB
GGUF
FA
Falcon H1 0.5B Instruct
Falcon · ggml-org
Params521M
Context16K
Smallest0.6 GB
GGUF
QW
LoRA Deepthink Reasoning Qwen2.5 7B Instruct Q8 0
Qwen · ggml-org
Params40M
Context—
Smallest0.2 GB
GGUF
LF
LFM2 test ci 80M
Lfm · ggml-org
Params81M
Context125K
Q4_K_M0.1 GB
Tool use
LF
LFM3-Omni-2B
Lfm · ggml-org
Params1.73B
Context125K
Q4_K_M1.1 GB
ReasoningTool useVision

Keep browsing