Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
magiccodingman
/
Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF
like
0
Text Generation
Safetensors
GGUF
qwen3
quantized
cpu
gpu
mxfp4
mxfp4_moe
mxfp4_hybrid
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF
/
Benchmarks
/
Qwen3-4B-Instruct-2507-F16
662 kB
1 contributor
History:
1 commit
magiccodingman
Add GGUF models
f5a18c6
about 1 month ago
llamabench.txt
Safe
775 Bytes
Add GGUF models
about 1 month ago
perplexity_code.txt
Safe
11.2 kB
Add GGUF models
about 1 month ago
perplexity_general.txt
Safe
10.9 kB
Add GGUF models
about 1 month ago
perplexity_math.txt
Safe
10.9 kB
Add GGUF models
about 1 month ago
ppl_corpus_code.txt
Safe
366 kB
Add GGUF models
about 1 month ago
ppl_corpus_general.txt
Safe
132 kB
Add GGUF models
about 1 month ago
ppl_corpus_math.txt
Safe
131 kB
Add GGUF models
about 1 month ago