Ternary-Bonsai-27B-mlx-2bit vs Llama-3.2-1B
Specs, VRAM requirements and download trends — updated 3 September 2026.
prism-ml · A · Open weights
Params
2.6 B
Context
—
30d
1.0 M
apache-2.0 · commercial OK
meta-llama · B · Open weights
Params
1.2 B
Context
—
30d
477 K
llama3.2 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Ternary-Bonsai-27B-mlx-2bit | Llama-3.2-1B |
|---|---|---|
| Parameters | 2.6 B | 1.2 B |
| Architecture | Qwen3_5ForConditionalGeneration | LlamaForCausalLM |
| Context length | — | — |
| Licence | apache-2.0 | llama3.2 |
| Commercial use | Allowed | Conditional |
| Languages | — | 8 |
| Downloads 30d | 1,012,597 | 477,238 |
| Downloads all time | 4.7 M | 60.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2026-07-04 | 2024-09-18 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.1 M432 K
Ternary-Bonsai-27B-mlx-2bit
Llama-3.2-1B
A overtook B on 15 Sep
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.2-1B · fp16
3.4 GB / 24 GB
Ternary-Bonsai-27B-mlx-2bit · fp16
10.2 GB / 24 GB