Q3_K_L GGUF models
3-bit k-quant, large. A little better than Q3_K_M at a slightly larger size. 101200 models have a Q3_K_L file. Sizes run from 1M to 1030B parameters. The longest trained context is 4194304K tokens.
GR
Granite 8b Code Instruct
Granite · duyntnet
Params8.05B
Context4K
Q4_K_M4.9 GB
VA
VanMach 7B
Vanmach · mradermacher
Params7.71B
Context128K
Q4_K_M4.8 GB
BO
Borealis 27b
Borealis · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
QW
Qwen3.6 21B IQ Ultra Heretic Uncensored Thinking
Qwen · mradermacher
Params20.8B
Context256K
Q4_K_M12.9 GB
SP
Spark X2.6 4B
Spark · mradermacher
Params4.11B
Context1024K
Q4_K_M2.6 GB
AI
aidc-ai-business_marcoroni-7b-v3
Aidc · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen2.5 VL 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
RO
RoGemma-7b-Instruct
Rogemma · legraphista
Params8.54B
Context8K
Smallest2.2 GB
QW
Qwen2-7B
Qwen · legraphista
Params7.62B
Context128K
Smallest1.9 GB
LL
Llama 3.3 8B Thinking Gemini Flash 11000x 128k
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
SA
Sage A1.5
Sage · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
GE
Big Tiger Gemma 27B v3
Gemma · bartowski
Params28.4B
Context128K
Q4_K_M17.3 GB
CO
Command A Plus 05 2026
Command · bartowski
Params218B
Context195K
Q4_K_M135.1 GB
LL
models--mergekit-community--Llama3-12B-wwe
Llama · MaziyarPanahi
Params13.7B
Context8K
Q4_K_M8.3 GB
MI
models--automerger--Experiment28T3q-7B
Mistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
MixtralOrochi8x7B i1
Mistral · mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
MI
emrgnt-cmplxty_mistral-7b-phibrarian-32k
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
Ministral 3 14B Reasoning 2512 Uncensored
Mistral · mradermacher
Params13.5B
Context256K
Q4_K_M8.2 GB
IN
Internlm2 Math Base 20b
InternLM · mradermacher
Params19.9B
Context8K
Q4_K_M12.0 GB
QW
Qwen2.5 1.5B Instruct Abliterated
Qwen · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
MA
Magnum v4 22b
Magnum · mradermacher
Params22.2B
Context32K
Q4_K_M13.3 GB
QW
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
FA
Falcon3 7B Instruct
Falcon · bartowski
Params7.46B
Context32K
Q4_K_M4.6 GB
GR
Granite 4.2 30b
Granite · bartowski
Params29.3B
Context128K
Q4_K_M18.0 GB
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · legraphista
Params15.7B
Context160K
Smallest5.0 GB
ME
G4 MeroMero 31B Uncensored Heretic
Meromero · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
AN
sao10k_ana-v1-m7
Ana · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
DE
Deepseek Coder 6.7B Instruct
DeepSeek · second-state
Params6.74B
Context16K
Q4_K_M4.1 GB
QW
Qwen3.8 27B Heretic JP Roleplay NSFW DanbooruTags
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
MI
Nous-Hermes-2-Mixtral-8x7B-SFT
Mistral · mradermacher
Params46.7B
Context32K
Q4_K_M28.4 GB