estimate, except measured file sizes

Can I run Mistral 7B v0.3 locally?

7.25B parameters. Parameter count is an estimate.

Licence:
not recorded
Context:
32,768 tokens
Modality:
not recorded
Released:
not recorded

Architecture is an estimate of the familiar 7B shape. No config was fetched for this dataset.

· Model page

Memory per quant

KV is at 8,192 tokens. Overhead is 0.8 GB. Both are estimates. A measured file size is labelled. The last column is the cheapest machine that fits the total fully.

Memory per quant for Mistral 7B v0.3
QuantFile sizeKV at 8K+0.8 overheadTotalCheapest full fit
Q87.8 GB est.1.1 GB est.0.8 GB est.9.6 GB est.GeForce RTX 3060 12GB, €257 (used (median of sold listings))
Q44.4 GB est.1.1 GB est.0.8 GB est.6.2 GB est.GeForce RTX 3060 12GB, €257 (used (median of sold listings))

Cheapest rig that fits

Q4, full: GeForce RTX 3060 12GB, €257 (used (median of sold listings))

Q4, slow, partly in system RAM: Nothing on our list of 29 machines fits this quant.

On a specific GPU

Can I run Mistral 7B v0.3 locally? VRAM per quant and cheapest rig (EU prices) · localLLMrig