GGUF models by TeichAI

60 GGUF models quantized by TeichAI on Hugging Face. Sizes run from 20M to 32.8B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3 14B Claude 4.5 Opus High Reasoning Distill
Qwen · TeichAI
Params14.8B
Context40K
Q4_K_M9.0 GB
Reasoning
GL
GLM 4.7 Flash Claude Opus 4.5 High Reasoning Distill
GLM · TeichAI
Params30B
Context198K
Q4_K_M18.1 GB
Reasoning
QW
Qwen3.8 27B Fable Distill
Qwen · TeichAI
Params27.3B
Context256K
Q4_K_M17.4 GB
CodingVision
QW
Qwen3 14B GPT 5.2 High Reasoning Distill
Qwen · TeichAI
Params14.8B
Context40K
Q4_K_M9.0 GB
Reasoning
DE
Qwen3 8B DeepSeek v3.2 Speciale Distill
DeepSeek · TeichAI
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
GE
Gemma 4 26B A4B It Claude Opus Distill v2
Gemma · TeichAI
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningVision
GE
Gemma 4 31B It Claude Opus Distill
Gemma · TeichAI
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningVision
GE
Gemma 4 31B It Claude Opus Distill v2
Gemma · TeichAI
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningVision
GE
Gemma 4 26B A4B It Claude Opus Distill
Gemma · TeichAI
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningVision
QW
Qwen3 14B Gemini 3 Pro Preview High Reasoning Distill
Qwen · TeichAI
Params14.8B
Context40K
Q4_K_M9.0 GB
Reasoning
DE
Qwen3 14B DeepSeek v3.2 Speciale Distill
DeepSeek · TeichAI
Params14.8B
Context40K
Q4_K_M9.0 GB
CodingReasoning
QW
Qwen3 4B Thinking 2507 MiMo V2 Flash Distill
Qwen · TeichAI
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen3 4B Thinking 2507 MiniMax M2.1 Distill
Qwen · TeichAI
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
GE
Gemma 4 31B Fable 5 Agent
Gemma · TeichAI
Params30.7B
Context256K
Q4_K_M18.7 GB
CodingVision
QW
Qwen3 4B Thinking MiniMax M2.1 Coder
Qwen · TeichAI
Params4.02B
Context256K
Q4_K_M2.5 GB
CodingReasoningTool use
QW
Qwen3 14B Claude Sonnet 4.5 Reasoning Distill
Qwen · TeichAI
Params14.8B
Context40K
Q4_K_M9.0 GB
Reasoning
QW
Qwen3.5 27B Claude Opus 4.6 Distill
Qwen · TeichAI
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
DE
Devstral Small 2505 Deepseek V3.2 Speciale Distill
DeepSeek · TeichAI
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingReasoningTool use
QW
Qwen3 8B Gemini 3 Pro Preview Distill
Qwen · TeichAI
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen3 8B GPT 5 Codex Distill
Qwen · TeichAI
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen3.6 27B Claude Opus Reasoning Distill
Qwen · TeichAI
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
Qwen3 8B Gpt 5.2 High Reasoning Distill
Qwen · TeichAI
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
DE
Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Code Distill
DeepSeek · TeichAI
Params4.02B
Context256K
Smallest4.3 GB
CodingReasoningTool use
QW
Qwen3 4B Instruct 2507 Claude Haiku 4.5 Distill
Qwen · TeichAI
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen3 8B Gemini 2.5 Flash Distill
Qwen · TeichAI
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen3.6 27B Fable 5 Experimental
Qwen · TeichAI
Params27.3B
Context256K
Q4_K_M17.4 GB
CodingReasoningTool use
QW
Qwen3.5 9B Fable 5 v1
Qwen · TeichAI
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
QW
Qwen3 8B Claude Sonnet 4.5 Reasoning Distill
Qwen · TeichAI
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen3 4B Thinking 2507 Gemini 2.5 Flash Distill
Qwen · TeichAI
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen3 4B Thinking 2507 GPT 5.2 High Reasoning Distill
Qwen · TeichAI
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use

About TeichAI on Hugging Face

TeichAI has published 60 GGUF models that ggufmodels.com tracks, across families such as Qwen, DeepSeek and Gemma. The most downloaded are Qwen3 14B Claude 4.5 Opus High Reasoning Distill, GLM 4.7 Flash Claude Opus 4.5 High Reasoning Distill and Qwen3.8 27B Fable Distill.

The quants TeichAI publishes most often are Q8_0 (56), Q4_K_M (49), Q3_K_M (47) and BF16 (47). Their Q4_K_M files range from 2.5 to 19.8 GB. Parameter counts run from 20M to 32.8B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has TeichAI published?

60 models are listed here, mainly from the Qwen, DeepSeek and Gemma families. The most downloaded is Qwen3 14B Claude 4.5 Opus High Reasoning Distill.

Which quants does TeichAI publish?

The most common are Q8_0 (56 models), Q4_K_M (49 models), Q3_K_M (47 models) and BF16 (47 models).

Keep browsing