GGUF models that fit in 8 GB

151917 GGUF language models have at least one quant whose estimated memory use is 8 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
QW
Qwen3 1.7B Instruct
Qwen · Qwen
Params1.72B
Context40K
Best fitQ8_0 3.3 GB
GGUF
GR
Parable Granite 4.1 3B Claude Fable 5
Granite · AnkitAI
Params3.4B
Context128K
Best fitF16 8.0 GB
ReasoningTool use
LL
Llama-3.2-3B-Instruct
Llama · unsloth
Params3.21B
Context128K
Best fitF16 7.9 GB
GGUF
GR
Parable Granite 4.1 8B Claude Fable 5
Granite · AnkitAI
Params8.38B
Context128K
Best fitQ5_K_M 7.8 GB
ReasoningTool use
QW
Qwen3.8 Flash Next Uncensored i1
Qwen · mradermacher
Params177B
Context—
Smallest0.6 GB
ReasoningTool useVision
GE
gemma-4-E2B-it
Gemma · ggml-org
Params4.65B
Context128K
Best fitQ8_0 5.5 GB
Vision
QW
Qwen_Qwen3.5 4B
Qwen · lmstudio-community
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
Vision
QW
Qwen2.5 14B Instruct
Qwen · bartowski
Params14.8B
Context32K
Best fitQ2_K 7.9 GB
GGUF
BG
bge-small-en-v1.5
BGE · CompendiumLabs
Params33M
Context512
Best fitF32 0.8 GB
Embedding
QW
Holo 3.1 35B A3B
Qwen · Hcompany
Params34.7B
Context256K
Q4_K_M21.3 GB
Vision
QW
Qwen3 Embedding 0.6b
Qwen · Qwen
Params596M
Context32K
Best fitF16 2.6 GB
Embedding
HO
Diplodocus preview 4
Horizon · OsaurusAI
Params9B
Context512K
Best fitQ4_K_M 8.0 GB
ReasoningTool use
DE
Deepseek-R1-0528-Qwen3-8B
DeepSeek · unsloth
Params8.19B
Context128K
Best fitQ5_K_M 7.6 GB
Reasoning
QW
Qwen3.8 27B Uncensored
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
ReasoningTool useVision
LL
Llama 3.2 1B Instruct
Llama · bartowski
Params1.24B
Context128K
Best fitF16 3.2 GB
GGUF
AL
all-MiniLM-L6-v2
All · second-state
Params23M
Context512
Best fitQ2_K 0.6 GB
Embedding
QW
Qwen3-0.6B
Qwen · unsloth
Params596M
Context40K
Best fitBF16 2.6 GB
GGUF
QW
Qwen3 4B
Qwen · bartowski
Params4B
Context32K
Best fitQ8_0 6.0 GB
GGUF
AL
all-MiniLM-L6-v2
All · leliuga
Params23M
Context512
Best fitF32 0.7 GB
CodingEmbedding
EM
Embeddinggemma 2
Embeddinggemma · unsloth
Params271M
Context256K
Best fitBF16 2.7 GB
EmbeddingVision
GE
gemma-4-E4B-it
Gemma · ggml-org
Params7.5B
Context128K
Best fitQ4_0 5.2 GB
Vision
NE
Nemotron 3 Embed 8B BF16
Nemotron · Abiray
Params7.95B
Context256K
Best fitQ5_K_M 7.3 GB
Embedding
QW
Qwen2.5 Omni 7B
Qwen · ggml-org
Params7.6B
Context32K
Best fitQ4_K_M 5.7 GB
Vision
TA
UI-TARS-1.5-7B
Tars · Mungert
Params7.6B
Context125K
Best fitQ6_K_M 7.2 GB
Vision
QW
Qwen3-8B
Qwen · unsloth
Params8.19B
Context40K
Best fitQ5_K_M 7.6 GB
GGUF
GE
gemma 4 E4B it qat
Gemma · unsloth
Params93M
Context128K
Best fitQ4_K_XL 4.8 GB
Vision
QW
Qwen3.6-35B-A3B
Qwen · ggml-org
Params1.9B
Context256K
Best fitBF16 4.9 GB
Vision
SN
snowflake arctic embed m v1.5
Snowflake · Snowflake
Params109M
Context512
Best fitF32 1.2 GB
Embedding
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · bartowski
Params7.62B
Context128K
Best fitQ6_K_L 7.5 GB
Reasoning
BG
bge-large-en-v1.5
BGE · CompendiumLabs
Params334M
Context512
Best fitF32 2.6 GB
Embedding

Other memory sizes

Keep browsing