Ling-3.0-tiny-MLX-4bit
bash curl -fsSL https://rapidmlx.com/install.sh bash rapid-mlx serve ling-3.0-tiny-4bit curl -s http://localhost:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{"model":"default","messages":[{"role":"user","content":"Say hello"}]}'
Params
7.9 B
Context
131,072
Downloads 30d
372 K
Likes
10
Download history
daily snapshots · 11 days372 K175 K
Oct 14Oct 17Oct 21Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | u32 | 4.4 GB | 6.6 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 128K ctx | 4.4 GB | 24.3 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/ling-3-0-tiny-mlx-4bit
{
"hf_id": "rapid-mlx/Ling-3.0-tiny-MLX-4bit",
"params_b": 7.89,
"context_length": 131072,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 371517,
"vram_estimates": [
{ "quant": "u32", "gb": 6.6 }
],
"updated_at": "2026-10-14T01:00:24Z"
}
Specifications
- Architecture
- BailingMoeV3ForCausalLM
- Parameters
- 7.9 B
- Tensor type
- U32
- Context length
- 131,072
- Vocabulary
- 157,184
- Layers / heads
- 24 / 16
- Licence
- mit
- First seen on the Hub
- 2026-08-11
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-14
Compare with any text-generation model
Popular comparisons
Appears in