Medium GGUF models

42835 GGUF models with roughly 10B to 34B parameters. Sizes run from 9.51B to 34B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8-27B
Qwen · unsloth
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
QW
Qwen3.8-27B
Qwen · huihui-ai
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
QW
Qwen3.8 27B Uncensored
Qwen · JonathanColetti
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
MI
MiniMax H3
Minimax · unsloth
Params20B
Context—
Q4_K_M18.2 GB
GGUF
QW
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP
Qwen · HauhauCS
Params30B
Context—
Smallest0.9 GB
GGUF
QW
Ternary Bonsai 2 27B
Qwen · prism-ml
Params27B
Context256K
Smallest5.9 GB
Vision
QW
Qwen3.8 27B
Qwen · byteshape
Params27.3B
Context256K
Smallest8.8 GB
Vision
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP
Qwen · DavidAU
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
GE
Gemma-4-12B-It
Gemma · unsloth
Params11.9B
Context256K
Q4_K_M7.1 GB
Vision
QW
Swift 1.5 Qwen3.8 27B GSQ RCO
Qwen · ukisai
Params27B
Context—
Smallest0.0 GB
Reasoning
LA
Laguna XS 2.1 APEX
Laguna · mudler
Params33.4B
Context256K
Smallest12.8 GB
Coding
QW
Qwen3.8-27B
Qwen · peculiar-ragdoll
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
QW
Qwen3.8 27B GSQ RCO
Qwen · ISTA-DASLab
Params27B
Context—
Smallest0.0 GB
Vision
GE
Gemma-4-26B-A4B-It
Gemma · unsloth
Params25.2B
Context256K
Q4_K_M16.9 GB
Vision
QW
Qwen_Qwen3.8 27B
Qwen · lmstudio-community
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
MI
MiniMax H3
Minimax · DeepBeepMeep
Params25.8B
Context—
Q4_K_M14.6 GB
GGUF
QW
Qwopus3.8 27B Flash V2
Qwopus · Jackrong
Params28B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
QW
ThinkingCap Qwen3.8 27B
Qwen · bottlecapai
Params27.3B
Context256K
Q4_K_M17.4 GB
ReasoningVision
GE
gemma 4 12B it qat q4 0
Gemma · google
Params11.9B
Context256K
Smallest7.0 GB
Vision
QW
Qwen2.5 32B Instruct
Qwen · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
QW
Qwen3.8-27B
Qwen · agentionai
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
WA
Wan2.2 I2V A14B
Wan · QuantStack
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
MU
Muse Glimmer 30B
Muse · unsloth
Params27.9B
Context128K
Smallest1.6 GB
Vision
GE
Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced
Gemma · HauhauCS
Params11.9B
Context256K
Q4_K_M7.4 GB
RoleplayVision
QW
Qwen Image Edit 2511
Qwen · unsloth
Params20.4B
Context—
Q4_K_M12.8 GB
GGUF
LT
LTX 2
Ltx · DeepBeepMeep
Params19B
Context—
Q4_K_M13.0 GB
GGUF
MI
MiniMax H3 Pruned
Minimax · Abiray
Params20.1B
Context—
Q4_K_M11.6 GB
GGUF
QW
Underdog Saluki 27B 1.0
Qwen · ConwayResearch
Params27B
Context256K
Smallest7.9 GB
Tool useVision
SI
Simplicio 27B
Simplicio · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingVision
QW
Swift 1.5 Qwen3.8 27B heretic GSQ RCO
Qwen · jegreene
Params27.3B
Context256K
Smallest9.6 GB
ReasoningTool useVision

What counts as a medium model?

On this site medium means roughly 10B to 34B parameters. A Q4_K_M file is usually 6 to 22 GB, so you need a 12 GB to 24 GB GPU. 42,835 models fit this class. The most downloaded are Qwen3.8-27B, Qwen3.8-27B and Qwen3.8 27B Uncensored.

Their Q4_K_M files run 0.0 to 150.2 GB. The families you will see most are Qwen (8111), Gemma (3493) and Mistral (2318). The size class sorts models by parameter count, so a model with more experts or a longer context can need more memory than its class suggests. The model pages show the real file sizes.

Frequently asked questions

How much VRAM does a medium GGUF model need?

A Q4_K_M file is usually 6 to 22 GB, so you need a 12 GB to 24 GB GPU.

Which medium GGUF model is the most popular?

By Hugging Face downloads, Qwen3.8-27B.

Other sizes

Keep browsing