GGUF models by Thireus

2513 GGUF models quantized by Thireus on Hugging Face. Sizes run from 275M to 5632B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3 4B Instruct 2507
Qwen · Thireus
Params4.02B
Context256K
Smallest1.7 GB
ReasoningTool use
QW
Qwen3 VL 235B A22B Thinking
Qwen · Thireus
Params235B
Context256K
Smallest132.4 GB
ReasoningTool useVision
GL
GLM 4.5 Air
GLM · Thireus
Params1203.2B
Context128K
Smallest49.2 GB
GGUF
KI
Kimi K2 Instruct 0905 THIREUS IQ1 S R4 SPECIAL SPLIT
Kimi · Thireus
Params970B
Context256K
Smallest193.9 GB
GGUF
QW
Qwen3 Coder 480B A35B Instruct
Qwen · Thireus
Params480B
Context256K
Smallest270.3 GB
CodingTool use
QW
Qwen3 235B A22B Thinking 2507
Qwen · Thireus
Params235B
Context256K
Smallest125.4 GB
ReasoningTool use
KI
Kimi K2 Instruct 0905 THIREUS IQ2 K R4 SPECIAL SPLIT
Kimi · Thireus
Params5376B
Context256K
Smallest305.4 GB
GGUF
KI
Kimi K2 Instruct 0905 THIREUS IQ3 K R4 SPECIAL SPLIT
Kimi · Thireus
Params1030B
Context256K
Smallest441.7 GB
GGUF
DE
DeepSeek R1 0528
DeepSeek · Thireus
Params672B
Context160K
Smallest714.4 GB
ReasoningTool use
GL
GLM 4.7 THIREUS IQ2 KS SPECIAL SPLIT
GLM · Thireus
Params3360B
Context198K
Smallest98.5 GB
GGUF
KI
Kimi K2 Thinking THIREUS Q6 K SPECIAL SPLIT
Kimi · Thireus
Params1030B
Context256K
Smallest581.0 GB
ReasoningTool use
QW
Qwen3 Coder 480B A35B Instruct
Qwen · Thireus
Params480B
Context256K
Smallest191.8 GB
CodingTool use
GL
GLM 4.5 Air
GLM · Thireus
Params160B
Context128K
Smallest36.0 GB
GGUF
QW
Qwen3 235B A22B Thinking 2507
Qwen · Thireus
Params235B
Context256K
Smallest193.0 GB
ReasoningTool use
QW
Qwen3 4B Instruct 2507
Qwen · Thireus
Params4.02B
Context256K
Smallest3.3 GB
ReasoningTool use
QW
Qwen3 4B Instruct 2507
Qwen · Thireus
Params4.02B
Context256K
Smallest1.5 GB
ReasoningTool use
QW
Qwen3 VL 235B A22B Instruct
Qwen · Thireus
Params235B
Context256K
Smallest63.0 GB
Tool useVision
QW
Qwen3 4B Instruct 2507
Qwen · Thireus
Params4.02B
Context256K
Smallest2.1 GB
ReasoningTool use
QW
Qwen3 4B Thinking 2507
Qwen · Thireus
Params4.02B
Context256K
Smallest0.9 GB
ReasoningTool use
QW
Qwen3 4B Thinking 2507
Qwen · Thireus
Params4.02B
Context256K
Smallest2.8 GB
ReasoningTool use
DE
DeepSeek R1 0528
DeepSeek · Thireus
Params5376B
Context160K
Smallest184.7 GB
Reasoning
GL
GLM 4.7 Flash
GLM · Thireus
Params29.9B
Context198K
Smallest30.2 GB
ReasoningTool use
QW
Qwen3 235B A22B Instruct 2507
Qwen · Thireus
Params235B
Context256K
Smallest249.9 GB
ReasoningTool use
QW
Qwen3 4B Thinking 2507
Qwen · Thireus
Params4.02B
Context256K
Smallest2.7 GB
ReasoningTool use
QW
Qwen3 235B A22B Thinking 2507
Qwen · Thireus
Params235B
Context256K
Smallest132.4 GB
ReasoningTool use
GL
GLM 4.5 Air
GLM · Thireus
Params130B
Context128K
Smallest48.5 GB
GGUF
QW
Qwen3 4B Thinking 2507
Qwen · Thireus
Params4.02B
Context256K
Smallest1.6 GB
ReasoningTool use
KI
Kimi K2 Instruct 0905 THIREUS Q3 K SPECIAL SPLIT
Kimi · Thireus
Params1030B
Context256K
Smallest441.7 GB
GGUF
QW
Qwen3 235B A22B Instruct 2507
Qwen · Thireus
Params235B
Context256K
Smallest132.4 GB
ReasoningTool use
QW
Qwen3 Coder 480B A35B Instruct
Qwen · Thireus
Params480B
Context256K
Smallest206.5 GB
CodingTool use

Keep browsing