Ternary-Bonsai-2-27B-gguf vs Llama-3.3-70B-Instruct
Specs, VRAM requirements and download trends — updated 23 October 2026.
prism-ml · A · Open weights
Params
27.0 B
Context
—
30d
2.5 M
apache-2.0 · commercial OK
meta-llama · B · Open weights
Params
70.6 B
Context
—
30d
219 K
llama3.3 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Ternary-Bonsai-2-27B-gguf | Llama-3.3-70B-Instruct |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 27.0 B | 70.6 B |
| Architecture | — | LlamaForCausalLM |
| Context length | 262,144 | 131,072 |
| Licence | apache-2.0 | llama3.3 |
| Commercial use | Allowed | Conditional |
| Languages | — | 8 |
| Downloads 30d | 2,484,375 | 219,021 |
| Downloads all time | 5.3 M | 14.8 M |
| Quantizations on the Hub | GGUF | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2026-09-16 | 2024-11-26 |
| API input price / 1M tokens | $0.075 | $0.10 |
| API output price / 1M tokens | $0.50 | $0.32 |
| Est. cost per 1M input + 1M output tokens | $0.58 | $0.42 |
| Cached input / 1M tokens | $0.038 | — |
| AA Intelligence Index | — | 7.7 |
| AA Coding Index | — | 11.9 |
| AA Agentic Index | — | — |
| Max output tokens | 32,768 | 16,384 |
| API providers | 1 | 10 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Ternary-Bonsai-2-27B-gguf
$0.58
Llama-3.3-70B-Instruct
$0.42
Llama-3.3-70B-Instruct is 1.4× cheaper at list price.
Download trend
Daily snapshots, last 35 days (19 Sep – 23 Oct)
4.9 M219 K
Ternary-Bonsai-2-27B-gguf
Llama-3.3-70B-Instruct
A overtook B on 20 Sep
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.3-70B-Instruct · fp16
166.3 GB / 24 GB