Can Mac M5 Pro 64G run K2 Horizon MoVA 36B-A4B?
Comfortable: GGUF Q6_K needs 33.0 GB at 4K, batch 1; headroom 15.0 GB.
Text input, FP16 KV cache, one card. Unified-memory capacity uses the GPU guide’s usable limit; negative headroom may require host offload. Speed source settings may differ from this 4K estimate.
Measured runs
No measured run for this pair. Sizing is an estimate, not a runtime test.
Quant memory at 4K
| Quant | Total GB | Verdict | Weight sizing |
|---|---|---|---|
| GGUF Q4_K_M | 24.2 | Comfortable | Verified file |
| GGUF Q5_K_M | 28.5 | Comfortable | Verified file |
| GGUF Q6_K | 33.0 | Comfortable | Verified file |
| GGUF Q8_0 | 42.5 | Tight | Verified file |
Context capacity · GGUF Q6_K
| Context | Total GB | Verdict |
|---|---|---|
| 4K | 33.0 | Comfortable |
| 16K | 35.5 | Comfortable |
| 32K | 38.8 | Comfortable |
| 128K | 58.5 | Does not fit |
Generation speed
GGUF Q6_K: 98 tok/s · Bandwidth ceiling (not measured)