Pick your GPU and a model, and we'll rank its quants from highest to lowest quality —
with the fit verdict, size, an estimated speed, and a plain-English note on what you give up
at each step down. No account needed.
1 · Your GPU
No matching GPU in the list — you can type the model manually.
Search for your card above (Apple Silicon routes to unified memory automatically).
Without a GPU we'll still show sizes and the quality guidance below.
Used to judge partial CPU offload when a quant overflows VRAM.
Save your rig for one-click answers.
Your rig lives in this browser. A free account keeps it across the calculator, model pages and this helper.
Lower precision shrinks the KV cache (fits more context).
The quant ladder, top to bottom
Highest quality first. Each step down trades quality for a smaller file. Pick a model above to see which
rungs actually fit your GPU, their sizes and estimated speeds.
F16Full 16-bit weights: no quantization loss at all, but roughly twice the size of an 8-bit quant and rarely worth it over Q8 for local use.
Q8_0Effectively lossless in community experience — the closest you get to the original model, at the largest practical GGUF size.
Q6_KVery close to Q8 in everyday use; the usual choice when Q8 is just too big to fit your memory.
Q5_K_MHigh quality with a noticeably smaller footprint than Q6 — a popular 'quality first, but it still fits' pick.
Q5_K_SA little smaller than Q5_K_M for a small quality trade; useful when you need to claw back some memory.
Q4_K_MThe community default: minor quality loss versus Q5/Q6, usually unnoticeable outside edge tasks, at a much smaller size.
Q4_K_SSlightly smaller than Q4_K_M for a modestly larger quality trade; handy when Q4_K_M just misses your VRAM.
IQ4_XSAn i-quant that packs 4-bit weights tighter than Q4_K_S — similar quality in community reports and a smaller file, though slightly heavier to decode on some runtimes.
Q3_K_MNoticeably lighter than Q4 with a real, more visible quality drop — a squeeze-it-in option rather than a default.
Q3_K_SSmaller and rougher than Q3_K_M; generally a last resort before dropping to Q2.
Q2_KThe smallest common quant — expect clearly degraded output. Community advice is usually to run a smaller model at a higher quant before choosing Q2.
Guidance reflects community experience, not measured benchmarks — quality loss is usually more noticeable on
smaller models than large ones.