prism-ml / text-generation updated 2 months ago

Bonsai-27B-mlx-1bit

Name: Bonsai-27B-mlx-1bit
Author: prism-ml

Prism ML Website    Whitepaper    Demo & Examples    Discord

Params

1.7 B

Context

—

Downloads 30d

1.1 M

Likes

251

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 50 days

▲ 693 K in the last 30 days (39.2%)

2.1 M204 K

Aug 3Aug 19Sep 5Sep 21

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	f16	5.1 GB	6.4 GB	✅ Runs comfortably

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 · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/bonsai-27b-mlx-1bit
{
  "hf_id": "prism-ml/Bonsai-27B-mlx-1bit",
  "params_b": 1.72,
  "context_length": null,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 1072514,
  "vram_estimates": [
    { "quant": "f16", "gb": 6.4 }
  ],
  "updated_at": "2026-08-03T01:00:24Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Qwen3_5ForConditionalGeneration
Parameters: 1.7 B
Tensor type: F16
Licence: apache-2.0
First seen on the Hub: 2026-07-04
Base model: Qwen3.6-27B
Training datasets: undisclosed
Added to our catalog: 2026-08-03

Family

Base model and the most-downloaded derivatives in the catalog.

Base Qwen3.6-27B Qwen 3.5 M

Compare with any text-generation model

Popular comparisons

Qwen3-0.6B 23.7 M Qwen2.5-1.5B-Instruct 7.4 M Qwen3-4B 6.9 M Llama-3.2-1B-Instruct 6.9 M Kimi-K3-DSpark 3.7 M Qwen3-1.7B 3.6 M