~/model/huggingfaceQwen/Qwen2.5-7B-Instruct
Alibaba provider

Qwen 2.5 7B

Alibaba's 7B reference. Strong multilingual; great FP16 fit on consumer cards.

Parameters
7B
Family
Alibaba
Context
128K tokens
FP16 weights
14GB
// where you can run it
qwen2.5:7bLM StudiovLLMMLXoMLX
// hugging face stats (cached daily)
13.3M downloads · 1K likes · license: apache-2.0 · updated 1 year ago

What you need to run this.

$ ./vrambudget --model qwen-2-5-7b --by quant
FP1614 GB
RTX 309024 GB · fitsRTX 3090 Ti24 GB · fitsRTX 409024 GB · fitsRX 7900 XTX24 GB · fits
Q8_07.4 GB
RTX 3060 12GB12 GB · fitsRTX 3080 Ti12 GB · fitsRTX 407012 GB · fitsRTX 4070 Super12 GB · fits
Q6_K5.7 GB
RTX 308010 GB · fitsRTX 3060 12GB12 GB · fitsRTX 3080 Ti12 GB · fitsRTX 407012 GB · fits
Q5_K_M4.8 GB
RTX 30708 GB · fitsRTX 40608 GB · fitsRTX 308010 GB · fitsRTX 3060 12GB12 GB · fits
Q4_K_M3.9 GB
RTX 30708 GB · fitsRTX 40608 GB · fitsRTX 308010 GB · fitsRTX 3060 12GB12 GB · fits

// budgets shown at ctx 8K, concurrency 1, 15% safety headroom. Tune in the calculator →

Alternatives at this size.

$ grep --params similar catalog.json
$ similarMistral 7B v0.37.2BMistral$ similarLlama 3.1 8B8BMeta$ similarGranite 8B Code8BIBM$ similarQwen 3.5 9B9BAlibaba

Discussion.

$ gh discussion list

// sign in with github to leave a comment. threads live in the repo's discussions tab.