Llama GGUF models
30050 GGUF models in the Llama family, quantized by 7365 uploaders. Sizes run from 1M to 1020B parameters. The longest trained context is 102400K tokens.
LL
Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
LL
Llama 3.2 3B Instruct Roleplay Tuned
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
LL
Llama 3 8B LexiFun Uncensored V1
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama 3.3 70B Instruct DASHQ Q2
Llama · jkim96
Params70.6B
Context128K
Smallest19.4 GB
LL
Llama-3-Luminurse-v0.1-OAS-8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama 3.2 3B Instruct
Llama · MCZK
Params3.21B
Context128K
Q4_K_M2.0 GB
LL
dolphin-2.9.1-llama-3-8b
Llama · crusoeai
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama 3.2 1b Abliterated
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
LL
Llama 3B Coder
Llama · koshuro
Params3.21B
Context128K
Q4_K_M2.0 GB
LL
nvidia/Llama-3.1-8B-UltraLong-1M-Instruct
Llama · DevQuasar-12
Params8.04B
Context1048K
Q4_K_M4.9 GB
LL
Sparse Llama 3.1 8B 2of4
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
LL
Infinity Instruct 7M Gen Llama3 1 8B
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama 2 7b EAX
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
LL
FineLlama 3.1 8B
Llama · mlabonne
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
Llama 3.1 KokoroChat Full i1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Meta Llama 3 8B Instruct
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama 3.1 8B Instuct Uz
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
llama 3 nvidia ChatQA 1.5 8B
Llama · QuantFactory
Params8B
Context8K
Q4_K_M4.9 GB
LL
Cogito v2 Preview Llama 109B MoE
Llama · bartowski
Params108B
Context256K
Q4_K_M67.7 GB
LL
Llama xLAM 2 70b Fc R
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Llama 3.3 70B Instruct Abliterated
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Strom Llama Merge
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
Hermes 3 Llama 3.1 8B
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
llama-3-Nephilim-v2-8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama3.1 8B Thinking R1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
Abliterated Llama 8b
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
Replete-Coder-Llama3-8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
ELYZA japanese Llama 2 13b fast instruct
Llama · mmnga
Params13.1B
Context4K
Q4_K_M8.0 GB
LL
Llama-3-8B-Instruct-UltraDPO3-NT
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Meta Llama 3 8B Instruct
Llama · mmnga
Params8.03B
Context8K
Q4_K_M4.9 GB