Can I run QuantFactory/MathCoder2-CodeLlama-7B-GGUF on M3 Mac 24 GB?

File-size estimate: within budget. Estimate only. No fresh, matching Proof Lab measurement is available for this file and device.

FILE-SIZE ESTIMATE

File-size estimate: within budget.

Estimate only. No fresh, matching Proof Lab measurement is available for this file and device.

Next, open the model page to check its files and available run instructions.

View model and files
File on disk
3.80 GiB
Memory allowance
4.75 GiB
Memory pool
unified memory
Evidence
Estimate only

The exact file

MathCoder2-CodeLlama-7B.Q4_K_M.gguf

File fingerprint

SHA-256

3b72122bdf0ce4ff0e5998e65cdef5f65c97a21f6b3ddc7809a536150c75ea86

File size × 1.25 = 4.75 GiB. The assumed budget is 22.00 GiB unified memory, after reserving 2 GiB. Context, runtime and other apps can need more.

Run command

No tested command for this file and device yet. Open the model page for available setup instructions.

Alternatives with room

No fitting alternatives in this sample. Find another model.

Questions about this run

Can I run QuantFactory/MathCoder2-CodeLlama-7B-GGUF on M3 Mac 24 GB?

File-size estimate: within budget. Estimate only. No fresh, matching Proof Lab measurement is available for this file and device.

How is memory fit calculated?

File size × 1.25 = 4.75 GiB. The assumed budget is 22.00 GiB unified memory, after reserving 2 GiB. Context, runtime and other apps can need more.

Was this exact file tested on this device?

No matching fresh lab evidence is available. File-size estimates do not establish runtime support.

Check another device for this model