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.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
LL
Single GPU Llama3 8B i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Schematron-3B
Llama · Mungert
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LL
Impish_LLAMA_3B
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
LL
Openbuddy Llama3.3 70b v24.1
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
llama3-8B-DarkIdol-2.1-Uncensored-1048K
Llama · mradermacher
Params8.03B
Context1024K
Q4_K_M4.9 GB
Roleplay
LL
Llama-3-8B-Magpie-Air-MT-SFT-v0.1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Evil Alpaca 3B L3.2
Llama · QuantFactory
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LL
Heretic Llama Deepsync 1B
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LL
Llama 3.1 8B Magpie Align v0.1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama-3.3-70B-Instruct
Llama · axana-labs
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
llama3 s instruct v0.2
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
magnum v2 4b
Llama · QuantFactory
Params4.51B
Context128K
Q4_K_M2.8 GB
GGUF
LL
llama 3.1 medprm reward v1.0
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama 3 6B v0
Llama · mradermacher
Params6.29B
Context8K
Q4_K_M3.9 GB
GGUF
LL
Fireball Llama 3.11 8B v2orpo i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Infinity Instruct 7M Gen Llama3_1 8B
Llama · second-state
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-Soliloquy-8B-v2
Llama · mradermacher
Params8.03B
Context24K
Q4_K_M4.9 GB
GGUF
LL
Scarlett Llama 3 8B v1.0
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Coding
LL
Llama 3.1 Unhinged Vision 8B
Llama · FiditeNemini
Params8.03B
Context8K
Smallest8.5 GB
Vision
LL
Llama 4 Scout 17B 16E Instruct
Llama · second-state
Params108B
Context10240K
Q4_K_M65.4 GB
Tool useVision
LL
Meta-Llama-3-70B-6-layers
Llama · mradermacher
Params7.24B
Context8K
Q4_K_M4.5 GB
GGUF
LL
llava llama 3 8b v1 1
Llama · RDson
Params8.03B
Context8K
Q4_K_M4.9 GB
Vision
LL
Sparse Llama 3.1 8B 2of4
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama3 Instruct OpenBioLLM 8B merged
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama 3 typhoon v1.5x 70b instruct i1
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Llama 3.2 8B Instruct i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama 3 Youko 70b Instruct
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
calme 2.1 llama3 70b
Llama · MaziyarPanahi
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Llama 3.2 3B small Shiro roleplay
Llama · samunder12
Params3.21B
Context128K
Q4_K_M2.0 GB
RoleplayTool use
LL
Llama3-ChatQA-1.5-8B
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF

Keep browsing