Written by Jakub Rusinowski · Last updated July 15, 2026
Yes, comfortably — you'll have ~6.2 GB of headroom running Ternary Bonsai 27B at Ternary (1.58-bit, ~1.71 bpw) (5.77125 GB, ~35 tok/s (est.)).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
| VRAM | 12 GB |
| Memory Bandwidth | 456 GB/s |
| Quant | VRAM needed | Fits 12 GB? | Max context |
|---|---|---|---|
| F16 | 55.7 GB | ✗ No | — |
| Q8_0 | 30.4 GB | ✗ No | — |
| Q6_K | 23.8 GB | ✗ No | — |
| Q5_K_M | 20.8 GB | ✗ No | — |
| Q4_K_M | 18 GB | ✗ No | — |
| Q3_K_M | 13.2 GB | ✗ No | — |
| Q2_K | 10.5 GB | ✓ Yes | 8K |
VRAM needed assumes a 4K-token context with an f16 KV cache; “Max context” is the largest window that still fits in 12 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
| Ternary Bonsai 27B | Ternary (1.58-bit, ~1.71 bpw) · 5.77125 GB · ~35 tok/s (est.) |
| 1-bit Bonsai 27B | 1-bit (binary, ~1.125 bpw) · 3.796875 GB · ~47 tok/s (est.) |
At 2 hrs/day, buying (~$249) beats renting at $0.34/hr after about 12 months.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Yes, comfortably — you'll have ~6.2 GB of headroom running Ternary Bonsai 27B at Ternary (1.58-bit, ~1.71 bpw) (5.77125 GB, ~35 tok/s (est.)).
Ternary Bonsai 27B at Ternary (1.58-bit, ~1.71 bpw) quantization (5.77125 GB), estimated ~35 tokens/sec.
| Size | VRAM | Verdict | Speed |
|---|---|---|---|
| Ternary Bonsai 27B | 5.8 GB | Runs | ~35 tok/s |
| 1-bit Bonsai 27B | 3.8 GB | Runs | ~47 tok/s |
← Can I Run It? | Bonsai 27B Model Page | Intel Arc B580 GPU Page | Check Your Hardware