Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
nisten
/
qwenv2-7b-inst-imatrix-gguf
like
3
GGUF
License:
apache-2.0
Model card
Files
Files and versions
Community
Use this model
d2b704a
qwenv2-7b-inst-imatrix-gguf
1 contributor
History:
19 commits
nisten
best speed/perplexity quant for mobile devices with 8bit acceleration
d2b704a
verified
24 days ago
.gitattributes
3.07 kB
best speed/perplexity quant for mobile devices with 8bit acceleration
24 days ago
8bitimatrix.dat
4.54 MB
LFS
calculated imatrix in 8bit, was jsut as good as f16 imatrix
24 days ago
README.md
1.55 kB
Update README.md
24 days ago
qwen7bv2inst_Iq4xs_output6k.gguf
4.22 GB
LFS
Standard IQ4XS quantizing down from full bf16 ( not from f16)
24 days ago
qwen7bv2inst_iq4xs_embedding8_outputq8.gguf
4.64 GB
LFS
great quant if your chip has 8bit acceleration, slightly better than 4k embedding
24 days ago
qwen7bv2inst_iq4xs_output8bit.gguf
4.35 GB
LFS
best speed/perplexity quant for mobile devices with 8bit acceleration
24 days ago
qwen7bv2inst_q4km_embeddingf16_outputf16.gguf
6.11 GB
LFS
Good speed reference quant for older CPUs, however not much improvement from f16 embedding
24 days ago
qwen7bv2inst_q4km_output8bit.gguf
4.82 GB
LFS
very good quant for speed/perplexity, embedding is at q4k
24 days ago
qwen7bv2instruct_bf16.gguf
15.2 GB
LFS
Rename qwen7bf16.gguf to qwen7bv2instruct_bf16.gguf
24 days ago
qwen7bv2instruct_q5km.gguf
5.58 GB
LFS
standard q5km conversions with 8bit output for reference.
24 days ago
qwen7bv2instruct_q8.gguf
8.1 GB
LFS
Best q8 conversion down from bf16 with slightly better perplexity than f16 based quants
24 days ago