maple-preview-GGUF
Variant GGUF size --- ---: TQ10 + Q4K head 4.64 GiB TQ10 + FP16 head 5.06 GiB TQ20 + Q4K head 5.50 GiB TQ20 + FP16 head 5.91 GiB
Params
—
Context
—
Downloads 30d
424 K
Likes
63
Download history
daily snapshots · 38 days
▲ 14 K in the last 30 days (3.1%)
446 K424 K
Aug 23Sep 2Sep 12Sep 21
446 K315 K
Aug 15Aug 27Sep 9Sep 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 |
|---|---|---|---|---|
| maple-preview-TQ1_0-head-F16.gguf | Q1_0 | 5.4 GB | 6.5 GB | ✅ Runs comfortably |
| maple-preview-TQ2_0-head-F16.gguf | Q2_0 | 6.3 GB | 7.5 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$ ollama run maple-preview-gguf # pin the quantization explicitly $ ollama run maple-preview-gguf-q1_0
$ huggingface-cli download deepgrove/maple-preview-GGUF-GGUF \
maple-preview-TQ1_0-head-F16.gguf --local-dir .
$ llama-cli -m maple-preview-TQ1_0-head-F16.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/maple-preview-gguf
{
"hf_id": "deepgrove/maple-preview-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 423694,
"vram_estimates": [
{ "quant": "Q1_0", "gb": 6.5 },
{ "quant": "Q2_0", "gb": 7.5 }
],
"updated_at": "2026-08-15T04:00:21Z"
}
Specifications
- Licence
- mit
- First seen on the Hub
- 2026-08-06
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-15
Compare with any text-generation model