Llama-3.2-3B-Instruct vs JiRackUltra_1b
Specs, VRAM requirements and download trends — updated 26 October 2026.
meta-llama · A · Open weights
Params
3.2 B
Context
—
30d
872 K
llama3.2 licence · conditional
CMSManhattan · B · Open weights
Params
1.8 B
Context
131,072
30d
891 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Llama-3.2-3B-Instruct | JiRackUltra_1b |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 3.2 B | 1.8 B |
| Architecture | LlamaForCausalLM | Qwen2ForCausalLM |
| Context length | 131,072 | 131,072 |
| Licence | llama3.2 | mit |
| Commercial use | Conditional | Allowed |
| Languages | 8 | 13 |
| Downloads 30d | 872,223 | 891,277 |
| Downloads all time | 50.9 M | 2.6 M |
| Quantizations on the Hub | SAFETENSORS | GGUF, SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-09-18 | 2026-08-02 |
| API input price / 1M tokens | $0.05 | not on OpenRouter |
| API output price / 1M tokens | $0.33 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.38 | not on OpenRouter |
| Cached input / 1M tokens | — | not on OpenRouter |
| AA Intelligence Index | — | not on OpenRouter |
| AA Coding Index | — | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 117,964 | not on OpenRouter |
| API providers | 2 | not on OpenRouter |
| Tool calling | No | not on OpenRouter |
| Reasoning mode | No | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Llama-3.2-3B-Instruct
$0.38
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.5 M307 K
Llama-3.2-3B-Instruct
JiRackUltra_1b
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
JiRackUltra_1b · Q4_K_M
2.0 GB / 24 GB
Llama-3.2-3B-Instruct · fp16
8.0 GB / 24 GB
JiRackUltra_1b · fp16 @ 128K ctx
8.7 GB / 24 GB