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
models--mergekit-community--mergekit-ties-aspkrwz
Llama · MaziyarPanahi
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
LL
Base Roblox coder Llama 3.2 1B vLLM i1
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
CodingTool use
LL
bugdaryan Code Llama 2 13B instruct text2sql
Llama · RichardErkhov
Params3.8B
Context—
Q4_K_M0.0 GB
Coding
LL
Llama 3.3 70B Instruct
Llama · etemiz
Params70.6B
Context128K
Smallest15.3 GB
Tool use
LL
Meta Llama 3 11.5B Instruct
Llama · mradermacher
Params11.5B
Context8K
Q4_K_M7.0 GB
GGUF
LL
Maestro R1 Llama 8B i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
LL
Llama 2 70b Chat Hf
Llama · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
LL
Openbuddy Llama3.2 1b v23.1 131k
Llama · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
GGUF
LL
Hermes 2 Pro Llama 3 8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Tool use
LL
Llama Deepsync 3B
Llama · QuantFactory
Params3.61B
Context128K
Q4_K_M2.2 GB
CodingTool use
LL
Malpyung_Meta Llama 3.1 8B_SFT
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.1 8B Instruct Uncensored
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama 3.1 8b Pruned 1 Layer
Llama · mradermacher
Params7.59B
Context128K
Q4_K_M4.6 GB
GGUF
LL
smol llama 220M openhermes
Llama · afrideva
Params218M
Context2K
Q4_K_M0.1 GB
Tool use
LL
Hypnos I1 8B Fp16
Llama · squ11z1
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningRoleplayTool use
LL
Llama-3.3-70B-Instruct
Llama · Mungert
Params70.6B
Context128K
Q4_K_M42.8 GB
Tool use
LL
Llama3.2 3B Enigma i1
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
CodingTool use
LL
Speechless Llama3.2 v0.1
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
LL
MLP KTLim llama 3 Korean Bllossom 8B
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
swap uniba LLaMAntino 2 chat 13b hf ITA
Llama · RichardErkhov
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
LL
SimNPO WMDP llama3 8b
Llama · tinyopsec
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.1 8B
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
meta llama CodeLlama 7b Python hf
Llama · RichardErkhov
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
LL
Mahou-1.4-llama3-8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
dolphin-2.9-llama3-70b
Llama · bartowski
Params70.6B
Context8K
Q4_K_M42.5 GB
CodingTool use
LL
Llama3 ElonMusk v1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
penny-llama3-2x8b-v2
Llama · mradermacher
Params13.7B
Context8K
Q4_K_M8.3 GB
GGUF
LL
Hermes-2-Pro-Llama-3-13B
Llama · mradermacher
Params12B
Context8K
Q4_K_M7.3 GB
Tool use
LL
Llama 3 Taiwan 70B Instruct Rc3
Llama · second-state
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Llama3.2 1B RolePlaying Full
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
RoleplayTool use

Keep browsing