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
MA
MangaLMM
Mangalmm · mradermacher
Params7.62B
Context125K
Best fitF16 16.2 GB
Vision
LL
dolphin 2.9 llama3 8b
Llama · dphn
Params8B
Context8K
Best fitQ8_0 10.1 GB
CodingTool use
QW
Qwen3.5 2B CyberSec
Qwen · reaperdoesntknow
Params1.94B
Context256K
Best fitBF16 4.8 GB
ReasoningTool useVision
ZA
Zawen v0.1 35B A3B
Zawen · mradermacher
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
Roleplay
MI
MiniMax M2.7
Minimax · bartowski
Params230B
Context192K
Q4_K_M138.8 GB
GGUF
QW
Atomic Chat / Qwen3.6 35B A3B
Qwen · AtomicChat
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
ReasoningTool use
MI
magistral-small-2509
Mistral · mistralai
Params23.6B
Context40K
Best fitQ8_0 26.9 GB
Reasoning
IN
InternLM2
InternLM · legraphista
Params19.9B
Context8K
Best fitBF16 41.8 GB
GGUF
QW
Qwen3.8 27B
Qwen · slothingaway
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
ReasoningTool useVision
CL
Clef Flash Heretic
Clef · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
Vision
QW
GELab-Zero-4B-preview
Qwen · Mungert
Params4B
Context256K
Best fitBF16 9.8 GB
Vision
QW
Qwen3 Vl 8b Heretic 1.3.0
Qwen · DreamFast
Params8.19B
Context256K
Best fitF16 18.1 GB
Vision
GR
Groot 19B A3B 261023
Groot · bartowski
Params19B
Context256K
Best fitBF16 39.2 GB
ReasoningTool useVision
QW
Huihui Qwen3 14B Abliterated v2
Qwen · mradermacher
Params14.8B
Context40K
Best fitQ6_K 14.0 GB
GGUF
QW
Qwen3.8 27B Q3 K M
Qwen · Chungulus
Params27.3B
Context256K
Best fitQ3_K_M 16.2 GB
Vision
QW
Carnice Qwen3.6 MoE 35B A3B APEX
Qwen · mudler
Params34.7B
Context256K
Smallest14.3 GB
Tool use
OR
Ornith 1.5 35B A3B MTP
Ornith · mradermacher
Params35.5B
Context256K
Best fitQ6_K 30.4 GB
CodingReasoning
QW
Qwen3.5 27B Heretic
Qwen · mradermacher
Params27B
Context256K
Best fitQ8_0 31.2 GB
CodingVision
CO
Confucius4 T3PO
Confucius · netease-youdao
Params14.8B
Context32K
Best fitF16 31.7 GB
GGUF
LL
Llama2 70B OASST SFT v10
Llama · TheBloke
Params69B
Context4K
Best fitQ4_K_M 44.6 GB
GGUF
DE
Deepseek Coder 6.7b Base
DeepSeek · mradermacher
Params6.74B
Context16K
Best fitQ6_K 10.3 GB
Coding
QW
Qwen2.5 14B Instruct
Qwen · mradermacher
Params14.8B
Context32K
Best fitQ6_K 14.2 GB
GGUF
HY
Hy MT2 1.8B
mradermacher
Params1.79B
Context256K
Best fitF16 4.6 GB
GGUF
PH
Phi 3 Medium 128k Instruct
Phi · bartowski
Params14B
Context128K
Best fitQ8_0 17.0 GB
Coding
MU
multilingual e5 small
Multilingual · cstr
Params118M
Context512
Smallest0.1 GB
Embedding
YI
Yi 34B 200K DARE megamerge v8 i1
Yi · mradermacher
Params34.4B
Context195K
Best fitQ6_K 30.7 GB
GGUF
PS
Psyonic Cetacean Ultra Quality 20b GGUF imat plus2
Psyonic · DavidAU
Params20B
Context4K
Best fitQ8_0 32.1 GB
Roleplay
TI
Tini Cybersec 8B A1B
Tini · bartowski
Params8.47B
Context125K
Best fitBF16 19.1 GB
Reasoning
GR
Granite 4.0 H Small
Granite · ibm-granite
Params32.2B
Context1024K
Best fitQ8_0 40.1 GB
GGUF
HO
K2-Horizon-7B
Horizon · bartowski
Params9B
Context512K
Best fitBF16 19.7 GB
GGUF

Other memory sizes

Keep browsing