GGUF models by Manojb

345 GGUF models quantized by Manojb on Hugging Face. Sizes run from 331M to 79.7B parameters. The longest trained context is 488K tokens.

Most downloadedNewestLargestLongest contextSmallest
LI
Ling Mini 2.0
Ling · Manojb
Params16.3B
Context32K
Smallest8.1 GB
ReasoningTool use
PH
phi 4 reasoning vision q4 k s
Phi · Manojb
Params14.7B
Context32K
Smallest8.4 GB
ReasoningVision
PH
phi 4 reasoning vision q4 K M
Phi · Manojb
Params14.7B
Context32K
Q4_K_M9.1 GB
ReasoningVision
QW
qwen3 8b.F16
Qwen · Manojb
Params8.19B
Context40K
Smallest16.4 GB
ReasoningTool use
LF
Lfm2-8B-A1B
Lfm · Manojb
Params8.34B
Context125K
Smallest8.9 GB
Tool use
QW
Qwen3.5-4B
Qwen · Manojb
Params4.21B
Context256K
Smallest2.6 GB
ReasoningTool useVision
LF
LFM2 24B A2B
Lfm · Manojb
Params23.8B
Context125K
Smallest13.5 GB
Tool use
QW
Qwen3.5 27B
Qwen · Manojb
Params26.9B
Context256K
Smallest15.7 GB
ReasoningTool use
GP
GPT OSS Swallow 20B RL v0.1
gpt-oss · Manojb
Params20.9B
Context128K
Smallest12.1 GB
Tool use
LI
Ling Mini 2.0
Ling · Manojb
Params16.3B
Context32K
Smallest9.4 GB
ReasoningTool use
LI
Ling Coder Lite
Ling · Manojb
Params16.8B
Context4K
Smallest10.6 GB
Coding
QW
Qwen3 4B Thinking 2507 GPT 5.2 High Reasoning Distill
Qwen · Manojb
Params4.02B
Context256K
Smallest8.1 GB
ReasoningTool use
NE
Nemotron Cascade 14B Thinking Claude 4.5 Opus Distill.q4 k m
Nemotron · Manojb
Params14.8B
Context32K
Q4_K_M9.0 GB
ReasoningTool use
LI
Ling Mini 2.0
Ling · Manojb
Params16.3B
Context32K
Smallest6.1 GB
ReasoningTool use
QW
Qwen3.5 27B Heretic v2
Qwen · Manojb
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
LF
LFM2 24B A2B
Lfm · Manojb
Params23.8B
Context125K
Smallest8.7 GB
Tool use
GL
GLM 4.7 Flash Uncen Hrt NEO CODE MAX imat D AU IQ2 M
GLM · Manojb
Params29.9B
Context198K
Smallest10.3 GB
CodingReasoningTool use
PH
phi 4 reasoning vision q5 k s
Phi · Manojb
Params14.7B
Context32K
Smallest10.2 GB
ReasoningVision
QW
qwen2.5 coder 7b instruct q8 0
Qwen · Manojb
Params7.62B
Context128K
Smallest8.1 GB
CodingTool use
QW
qwen2.5 coder 14b instruct q8 0
Qwen · Manojb
Params14.8B
Context128K
Smallest15.7 GB
CodingTool use
NE
Nemotron Cascade 14B Thinking Claude 4.5 Opus Distill.iq4 nl
Nemotron · Manojb
Params14.8B
Context32K
Smallest8.5 GB
ReasoningTool use
LI
Ling Coder Lite
Ling · Manojb
Params16.8B
Context4K
Smallest8.0 GB
Coding
LF
LFM2.5 1.2B Instruct F16
Lfm · Manojb
Params1.17B
Context125K
Smallest2.3 GB
Tool use
GP
GPT OSS Swallow 20B RL v0.1
gpt-oss · Manojb
Params20.9B
Context128K
Smallest13.3 GB
Tool use
QW
qwen2.5 coder 14b instruct q6 k
Qwen · Manojb
Params14.8B
Context128K
Smallest12.1 GB
CodingTool use
LI
Ling Coder Lite
Ling · Manojb
Params16.8B
Context4K
Smallest9.6 GB
Coding
LI
Ling Coder Lite
Ling · Manojb
Params16.8B
Context4K
Smallest8.1 GB
Coding
LI
Ling Mini 2.0
Ling · Manojb
Params16.3B
Context32K
Smallest11.3 GB
ReasoningTool use
NE
Nemotron Cascade 8B Thinking Claude 4.5 Opus Distill.q8 0
Nemotron · Manojb
Params8.19B
Context32K
Smallest8.7 GB
ReasoningTool use
LI
Ling Coder Lite
Ling · Manojb
Params16.8B
Context4K
Smallest7.6 GB
Coding

Keep browsing