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
VI
Viking-33B
Viking · mradermacher
Params33B
Context4K
Best fitQ6_K 29.6 GB
Coding
YI
ehartford_dolphin-2_2-yi-34b
Yi · TheBloke
Params34.4B
Context16K
Best fitQ8_0 39.1 GB
GGUF
OP
openchat_openchat-3.5-1210
Openchat · TheBloke
Params7.24B
Context8K
Best fitQ8_0 9.3 GB
Coding
MI
MiniCPM V 4_6 Thinking
MiniCPM · openbmb
Params752M
Context256K
Best fitF16 2.4 GB
ReasoningVision
CL
Clover-35B-A3B-Preview
Clover · Diffuspace
Params34.7B
Context128K
Best fitQ8_0 39.0 GB
ReasoningTool use
HU
humanizer-12b
Humanizer · ngquocvinh
Params11.9B
Context256K
Best fitQ8_0 26.1 GB
GGUF
AE
AesCode 8B
Aescode · mradermacher
Params8.19B
Context256K
Best fitQ6_K 8.4 GB
Coding
JI
Jina Embeddings v5 Text Nano Text Matching
Jina · jinaai
Params212M
Context8K
Best fitF16 1.2 GB
CodingEmbedding
GE
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Gemma · kamjin
Params7.5B
Context128K
Best fitQ8_K 10.0 GB
Vision
QW
Qwen3.6 35B A3B Uncensored MTP
Qwen · mecha-factory
Params35.5B
Context256K
Best fitQ4_K_M 22.9 GB
ReasoningTool useVision
OR
Ornith 1.0 9B
Ornith · bartowski
Params8.95B
Context256K
Best fitBF16 19.5 GB
Vision
QW
JoyFox Qwen3.6 35B A3B RP Aggressive
Qwen · mradermacher
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
RoleplayVision
LF
LFM3-VL-2B
Lfm · lmstudio-community
Params1.73B
Context125K
Best fitQ8_0 4.0 GB
ReasoningTool useVision
GR
Granite-4.0-H-Small
Granite · unsloth
Params32.2B
Context1024K
Best fitQ8_K_XL 43.9 GB
GGUF
GE
Gemma 4 31B It Scotoma 2
Gemma · bartowski
Params30.7B
Context256K
Best fitIQ3_M 47.8 GB
Vision
LL
LLaMA Mesh
Llama · bartowski
Params8B
Context128K
Best fitF16 17.6 GB
GGUF
QW
Whittle Qwen 3.8 35B A3B
Qwen · mradermacher
Params35.5B
Context256K
Best fitQ6_K 30.5 GB
CodingReasoning
MI
Ministral 3 8B Instruct 2512
Mistral · bartowski
Params8.49B
Context256K
Best fitBF16 18.6 GB
Vision
BG
Bge Small En v1.5
BGE · ggml-org
Params33M
Context512
Best fitQ8_0 0.7 GB
Embedding
QW
Qwen2.5 VL 32B Geometry
Qwen · mradermacher
Params32.8B
Context125K
Best fitQ8_0 37.5 GB
Vision
QW
UnifiedReward Edit Qwen35 27b
Qwen · mradermacher
Params26.9B
Context256K
Best fitQ8_0 31.2 GB
ReasoningTool useVision
AE
AesCode 8B
Aescode · prithivMLmods
Params8.19B
Context256K
Best fitBF16 18.1 GB
CodingVision
LL
tulu v1 llama2 70b i1
Llama · mradermacher
Params69B
Context2K
Best fitQ4_K_M 44.6 GB
GGUF
JA
Jan-nano-128k
Jan · Menlo
Params4B
Context128K
Best fitQ8_0 6.0 GB
GGUF
PH
Phi 3 mini 128k instruct
Phi · QuantFactory
Params3.82B
Context128K
Best fitQ8_0 7.8 GB
Coding
PH
Phi 3 Medium 128k Instruct
Phi · mradermacher
Params14B
Context128K
Best fitQ6_K 13.6 GB
Coding
DE
DeepSeek R1 Distill Qwen 7B Abliterated v2
DeepSeek · Melvin56
Params7.62B
Context128K
Best fitF16 16.2 GB
Reasoning
AI
airoboros-65b-gpt4-2.0
Airoboros · mradermacher
Params65B
Context2K
Best fitIQ3_XXS 46.6 GB
GGUF
LF
LFM2.5 8B A1B DSpark Draft v1
Lfm · LiquidAI
Params328M
Context125K
Best fitF16 1.2 GB
GGUF
AV
Avrik Pro 12B
Avrik · mradermacher
Params11.9B
Context256K
Best fitQ6_K 23.2 GB
GGUF

Other memory sizes

Keep browsing