GGUF models by DhruvalLabs

57 GGUF models quantized by DhruvalLabs on Hugging Face. Sizes run from 494M to 177B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8 27B
Qwen · DhruvalLabs
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
QW
Qwen2.5 VL 7B Instruct
Qwen · DhruvalLabs
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
GE
Gemma 4 12B
Gemma · DhruvalLabs
Params11.9B
Context256K
Q4_K_M7.4 GB
Vision
QW
Qwen2.5 VL 3B Instruct
Qwen · DhruvalLabs
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
QW
Qwen3 Coder 30B A3B Instruct
Qwen · DhruvalLabs
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
QW
Qwen AgentWorld 35B A3B
Qwen · DhruvalLabs
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
QW
Qwen3 0.6B
Qwen · DhruvalLabs
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
QW
Qwen3 4B Instruct 2507
Qwen · DhruvalLabs
Params4B
Context256K
Q4_K_M2.5 GB
GGUF
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · DhruvalLabs
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
QW
Qwen2.5 1.5B Instruct
Qwen · DhruvalLabs
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
QW
Qwen2.5 7B Instruct
Qwen · DhruvalLabs
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
KI
Kimi Linear 48B A3B Instruct
Kimi · DhruvalLabs
Params49.1B
Context1024K
Q4_K_M29.7 GB
CodingTool use
GL
GLM 4.7 Flash
GLM · DhruvalLabs
Params29.9B
Context198K
Q4_K_M18.1 GB
ReasoningTool use
QW
Qwen2.5 Coder 7B Instruct
Qwen · DhruvalLabs
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
QW
Qwen3.8 Flash Next
Qwen · DhruvalLabs
Params177B
Context256K
Q4_K_M238.3 GB
ReasoningTool use
QW
Qwen2.5 Coder 32B Instruct
Qwen · DhruvalLabs
Params32.8B
Context32K
Q4_K_M19.9 GB
CodingTool use
QW
Qwen3 8B
Qwen · DhruvalLabs
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen2.5 0.5B Instruct
Qwen · DhruvalLabs
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · DhruvalLabs
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
LF
LFM2.5 8B A1B
Lfm · DhruvalLabs
Params8.47B
Context125K
Q4_K_M5.2 GB
ReasoningTool use
PH
phi 4
Phi · DhruvalLabs
Params14.7B
Context16K
Q4_K_M9.1 GB
Coding
QW
Qwen3 4B Thinking 2507
Qwen · DhruvalLabs
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen3 32B
Qwen · DhruvalLabs
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
ST
Stable Code 3b
Stable · DhruvalLabs
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
PH
phi 2
Phi · DhruvalLabs
Params2.78B
Context2K
Q4_K_M1.7 GB
Coding
QW
WebWorld 8B
Qwen · DhruvalLabs
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
MI
Mistral 7B Instruct v0.1
Mistral · DhruvalLabs
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 8b Claude Agentic Fable5
Qwen · DhruvalLabs
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
PH
Phi 3 Mini 128k Instruct
Phi · DhruvalLabs
Params3.82B
Context128K
Q4_K_M2.4 GB
Coding
QW
LocateAnything 3B
Qwen · DhruvalLabs
Params3.4B
Context32K
Q4_K_M2.1 GB
CodingTool useVision

About DhruvalLabs on Hugging Face

DhruvalLabs has published 57 GGUF models that ggufmodels.com tracks, across families such as Qwen, Phi and Mistral. The most downloaded are Qwen3.8 27B, Qwen2.5 VL 7B Instruct and Gemma 4 12B.

The quants DhruvalLabs publishes most often are Q4_K_M (57), Q8_0 (56), Q6_K (56) and Q5_K_S (56). Their Q4_K_M files range from 0.0 to 238.3 GB. Parameter counts run from 494M to 177B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has DhruvalLabs published?

57 models are listed here, mainly from the Qwen, Phi and Mistral families. The most downloaded is Qwen3.8 27B.

Which quants does DhruvalLabs publish?

The most common are Q4_K_M (57 models), Q8_0 (56 models), Q6_K (56 models) and Q5_K_S (56 models).

Keep browsing