GGUF models that fit in 48 GB

201364 GGUF language models have at least one quant whose estimated memory use is 48 GB or less at 8K context. Each card shows the largest quant that fits. Sizes run from 1M to 20260731B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
SA
Sarashina2.2 3b Instruct v0.1
Sarashina · mmnga
Params3.36B
Context8K
Best fitQ8_0 5.4 GB
GGUF
QW
Qwen3 VL Embedding 8B
Qwen · mradermacher
Params7.57B
Context256K
Best fitF16 16.9 GB
EmbeddingVision
JA
NT Java 1.1B
Java · InfosysEnterprise
Params1.24B
Context8K
Q4_K_M0.8 GB
Coding
MA
manaca 1b base
Manaca · NANI-Nithin
Params1.72B
Context4K
Best fitBF16 4.4 GB
GGUF
AI
airoboros l2 13b gpt4 2.0
Airoboros · TheBloke
Params13B
Context4K
Best fitQ8_0 21.0 GB
GGUF
NE
NVIDIA-Nemotron-3-Nano-30B-A3B
Nemotron · vultr
Params31.6B
Context1024K
Best fitQ5_K_M 36.1 GB
ReasoningTool use
OP
openbuddy_openbuddy-zephyr-7b-v14.1
Openbuddy · TheBloke
Params7.28B
Context32K
Best fitQ8_0 9.3 GB
GGUF
LO
LongWriter Zero 32B
Longwriter · bartowski
Params32.8B
Context32K
Best fitQ8_0 37.5 GB
GGUF
LL
Llama-3_3-Nemotron-Super-49B-V1_5
Llama · unsloth
Params49.9B
Context128K
Best fitQ6_K 46.3 GB
GGUF
QW
Qwen3.5 122B A10B Abliterix
Qwen · mradermacher
Params122B
Context256K
Best fitQ2_K 46.2 GB
GGUF
QW
Qwen3.8 27B Abliterated
Qwen · mradermacher
Params27B
Context256K
Best fitQ8_0 31.2 GB
GGUF
QW
Qwen3-30B-A3B-128K
Qwen · unsloth
Params30.5B
Context128K
Best fitQ8_K_XL 37.3 GB
GGUF
CH
AA Chameleon 7b Plus
Chameleon · mradermacher
Params7B
Context4K
Best fitQ6_K 10.6 GB
GGUF
QW
Qwen3 4b Z Image Engineer V4
Qwen · BennyDaBall
Params4B
Context40K
Best fitF16 9.8 GB
GGUF
GE
Gemma 3n E2B It
Gemma · bartowski
Params4.46B
Context32K
Best fitQ8_0 5.8 GB
GGUF
LL
calme 2.2 llama3 70b
Llama · MaziyarPanahi
Params70.6B
Context8K
Best fitQ4_K_M 45.7 GB
GGUF
QW
Huihui Qwen3.8 Flash Next abliterated MTP
Qwen · htdohk
Params177B
Context256K
Best fitBF16 9.1 GB
ReasoningVision
ME
G4 MeroMero 31B Uncensored Heretic
Meromero · llmfan46
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
Vision
QW
Qwen3.8 27B Uncensored noMTP Q4 K M OpenCode
Qwen · oceanonline
Params27B
Context256K
Best fitQ4_K_M 19.2 GB
Tool use
SU
Sulphur 2 Prompt Enhancer Uncensored
Sulphur · PeppX
Params8.95B
Context256K
Best fitQ4_K_M 7.2 GB
Vision
QW
Qwopus3.5 9B v3
Qwen · Jackrong
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
ReasoningVision
SH
Shadow-Siren-14B-v2-Pruned
Shadow · mradermacher
Params13.8B
Context256K
Best fitQ6_K 20.9 GB
Roleplay
AI
jondurbin_airoboros-c34b-3.1.2
Airoboros · TheBloke
Params33.7B
Context16K
Best fitQ8_0 38.0 GB
GGUF
QW
Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context128K
Best fitQ6_K 7.2 GB
Roleplay
IN
InternVL3_5 38B
Internvl · bartowski
Params32.8B
Context40K
Best fitQ8_0 37.5 GB
Vision
PH
Phi 3 Medium 4k Instruct
Phi · mradermacher
Params14B
Context4K
Best fitQ6_K 13.6 GB
Coding
IN
InternVL3_5 38B
Internvl · mradermacher
Params32.8B
Context40K
Best fitQ8_0 37.5 GB
CodingVision
QW
Qwen2.5 32B
Qwen · mradermacher
Params32.8B
Context128K
Best fitQ6_K 29.5 GB
GGUF
LF
LFM2.5 1.2B JP 202606
Lfm · LiquidAI
Params1.17B
Context125K
Best fitF16 3.9 GB
GGUF
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · nyan-ame
Params7.6B
Context32K
Best fitF16 16.2 GB
Coding

Other memory sizes

Keep browsing