General model by hf1bitllm · 100B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro, Mac mini M5 Pro
Llama3 8B 1.58 100B tokens needs at least 34.5 GiB, more than the 20.6 GiB available for models, so it needs a Mac with more memory.
Specifications
GGUF Sources
Unvalidated forecasts for an 8K text context under a declared full-GPU scenario, at the lowest GPU bin sold with the chosen memory. Memory is reported as its components: exact artifact bytes and a KV allocation derived from a declared attention layout where the catalog carries them, a parameter proxy with no error bound where it does not, and the runtime's working memory, which a browser cannot measure. A fit is confirmed only when every component is known, so a model whose known memory fits reads "Fit unconfirmed" until ToolPiper measures it on your Mac, and one whose known memory alone exceeds the budget reads "Won't fit". Estimated speed ignores prompt length and prefill, and can overstate long-context performance. No measured speed error range is available. The recommendation score weighs declared preferences, not measured answer quality, and becomes a range where evidence is missing.
| Quantization | Memory | Speed | Verdict |
|---|---|---|---|
| Q8_0 | at least 97.8 GiB | ~2 tok/s · Estimated | Won't fit |
| Q6_K | at least 74.5 GiB | ~2 tok/s · Estimated | Won't fit |
| Q5_K_M | at least 63.3 GiB | ~2 tok/s · Estimated | Won't fit |
| Q4_K_M | at least 54.0 GiB | ~3 tok/s · Estimated | Won't fit |
| Q3_K_M | at least 44.7 GiB | ~4 tok/s · Estimated | Won't fit |
| Q2_K | at least 34.5 GiB | ~5 tok/s · Estimated | Won't fit |
Affiliate disclosure: the shop icons in this table are Amazon affiliate links. As an Amazon Associate, ModelPiper earns from qualifying purchases. Every fit rating, quantization and tok/s figure below is computed from the hardware specs and is not influenced by that.
Unvalidated forecasts for an 8K text context under a declared full-GPU scenario, at the lowest GPU bin sold with the chosen memory. Memory is reported as its components: exact artifact bytes and a KV allocation derived from a declared attention layout where the catalog carries them, a parameter proxy with no error bound where it does not, and the runtime's working memory, which a browser cannot measure. A fit is confirmed only when every component is known, so a model whose known memory fits reads "Fit unconfirmed" until ToolPiper measures it on your Mac, and one whose known memory alone exceeds the budget reads "Won't fit". Estimated speed ignores prompt length and prefill, and can overstate long-context performance. No measured speed error range is available. The recommendation score weighs declared preferences, not measured answer quality, and becomes a range where evidence is missing.
Minimum Mac
Q2_K · ~9 tok/s · 72% RAM · Fit unconfirmed
Known memory leaves the good-fit margin free; the runtime's working memory is not measured.
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper free