Hy3-GGUF
Dedicated to building a more intuitive, comprehensive, and efficient LLMs compression toolkit.
Params
—
Context
—
Downloads 30d
439 K
Likes
179
Download history
daily snapshots · 10 days439 K382 K
Jul 28Jul 31Aug 3Aug 6
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 |
|---|---|---|---|---|
| Hy3-IQ1_M-mtp.gguf | IQ1_M | 91.8 GB | 101.4 GB | ❌ Won’t fit |
| Hy3-Q2_K_XL-mtp.gguf | Q2_K_XL | 101.6 GB | 112.2 GB | ❌ Won’t fit |
| Hy3-Q3_K_M-mtp.gguf | Q3_K_M | 136.5 GB | 150.6 GB | ❌ Won’t fit |
| Hy3-Q4_K_M-mtp.gguf | Q4_K_M | 184.7 GB | 203.6 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$ ollama run hy3-gguf-angelslim # pin the quantization explicitly $ ollama run hy3-gguf-angelslim-q4_k_m
$ huggingface-cli download AngelSlim/Hy3-GGUF-GGUF \
Hy3-Q4_K_M-mtp.gguf --local-dir .
$ llama-cli -m Hy3-Q4_K_M-mtp.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/hy3-gguf-angelslim
{
"hf_id": "AngelSlim/Hy3-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 439228,
"vram_estimates": [
{ "quant": "IQ1_M", "gb": 101.4 },
{ "quant": "Q2_K_XL", "gb": 112.2 }
],
"updated_at": "2026-07-28T18:05:59Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2026-07-13
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.