Qwen3-14B vs Ornith-1.5-9B-MLX-4bit
Specs, VRAM requirements and download trends — updated 10 November 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-14B | Ornith-1.5-9B-MLX-4bit |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 14.8 B | 9.0 B |
| Architecture | Qwen3ForCausalLM | Qwen3_5ForConditionalGeneration |
| Context length | 40,960 | — |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | — | 1 |
| Downloads 30d | 12,904,408 | 264,848 |
| Downloads all time | 46.1 M | 714 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2026-08-18 |
| API input price / 1M tokens | $0.10 | not on OpenRouter |
| API output price / 1M tokens | $0.22 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.32 | not on OpenRouter |
| Cached input / 1M tokens | — | not on OpenRouter |
| AA Intelligence Index | — | not on OpenRouter |
| AA Coding Index | 13.8 | not on OpenRouter |
| AA Agentic Index | 0.9 | not on OpenRouter |
| Max output tokens | 36,864 | not on OpenRouter |
| API providers | 2 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-14B
$0.32
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
13.0 M205 K
Qwen3-14B
Ornith-1.5-9B-MLX-4bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Ornith-1.5-9B-MLX-4bit · fp16
7.4 GB / 24 GB
Qwen3-14B · fp16
35.2 GB / 24 GB