Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
geoffmunn
/
Qwen3-4B
like
3
Text Generation
GGUF
10 languages
qwen
qwen3
qwen3-4b
qwen3-4b-gguf
llama.cpp
quantized
reasoning
agent
chat
multilingual
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
e33dd7f
Qwen3-4B
23.8 GB
1 contributor
History:
22 commits
geoffmunn
Quality & Performance updated
e33dd7f
verified
about 2 months ago
Qwen3-4B-Q2_K
Quality & Performance updated
about 2 months ago
Qwen3-4B-Q3_K_M
Quality & Performance updated
about 2 months ago
Qwen3-4B-Q3_K_S
Quality & Performance updated
about 2 months ago
Qwen3-4B-Q4_K_M
Quality & Performance updated
about 2 months ago
Qwen3-4B-Q4_K_S
Quality & Performance updated
about 2 months ago
Qwen3-4B-Q5_K_M
Quality & Performance updated
about 2 months ago
Qwen3-4B-Q5_K_S
Quality & Performance updated
about 2 months ago
Qwen3-4B-Q6_K
Add Q2–Q8_0 quantized models with per-model cards, MODELFILE, CLI examples, and auto-upload
2 months ago
Qwen3-4B-Q8_0
Add Q2–Q8_0 quantized models with per-model cards, MODELFILE, CLI examples, and auto-upload
2 months ago
.gitattributes
Safe
2.12 kB
Add Q2–Q8_0 quantized models with per-model cards, MODELFILE, and auto-upload
3 months ago
MODELFILE
Safe
564 Bytes
Add Q2–Q8_0 quantized models with per-model cards, MODELFILE, CLI examples, and auto-upload
2 months ago
Qwen3-4B-f16:Q2_K.gguf
Safe
1.67 GB
xet
Add Q2–Q8_0 quantized models with per-model cards, MODELFILE, and auto-upload
3 months ago
Qwen3-4B-f16:Q3_K_M.gguf
Safe
2.08 GB
xet
Add Q2–Q8_0 quantized models with per-model cards, MODELFILE, and auto-upload
3 months ago
Qwen3-4B-f16:Q3_K_S.gguf
Safe
1.89 GB
xet
Add Q2–Q8_0 quantized models with per-model cards, MODELFILE, and auto-upload
3 months ago
Qwen3-4B-f16:Q4_K_M.gguf
Safe
2.5 GB
xet
Add Q4/Q5 quantized models with embedded metadata and auto-upload
3 months ago
Qwen3-4B-f16:Q4_K_S.gguf
Safe
2.38 GB
xet
Add Q4/Q5 quantized models with embedded metadata and auto-upload
3 months ago
Qwen3-4B-f16:Q5_K_M.gguf
Safe
2.89 GB
xet
Add Q4/Q5 quantized models with embedded metadata and auto-upload
3 months ago
Qwen3-4B-f16:Q5_K_S.gguf
Safe
2.82 GB
xet
Add Q4/Q5 quantized models with embedded metadata and auto-upload
3 months ago
Qwen3-4B-f16:Q6_K.gguf
Safe
3.31 GB
xet
Add Q2–Q8_0 quantized models with per-model cards, MODELFILE, and auto-upload
3 months ago
Qwen3-4B-f16:Q8_0.gguf
Safe
4.28 GB
xet
Add Q2–Q8_0 quantized models with per-model cards, MODELFILE, and auto-upload
3 months ago
Qwen3-4b-analysis.md
Safe
112 kB
Create Qwen3-4b-analysis.md
2 months ago
README.md
Safe
3.57 kB
Link to analysis added
2 months ago
SHA256SUMS.txt
Safe
813 Bytes
Add Q2–Q8_0 quantized models with per-model cards, MODELFILE, and auto-upload
3 months ago
