Agents-A1-4B-Q4_K_M-GGUF
> [!Note] > This repository contains model weights and configuration files for Agents-A1 in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc.
Params
4.0 B
Context
—
Downloads 30d
185 K
Likes
51
Download history
daily snapshots · 32 days
▲ 2 K in the last 30 days (1.0%)
188 K178 K
Sep 26Oct 6Oct 16Oct 25
188 K178 K
Sep 24Oct 4Oct 15Oct 25
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 |
|---|---|---|---|---|
| Agents-A1-4B-mmproj.gguf | GGUF | 0.7 GB | 1.8 GB | ✅ Runs comfortably |
| Agents-A1-4B-Q4_K_M.gguf | Q4_K_M | 2.7 GB | 4.1 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 agents-a1-4b-q4-k-m-gguf # pin the quantization explicitly $ ollama run agents-a1-4b-q4-k-m-gguf-q4_k_m
$ huggingface-cli download InternScience/Agents-A1-4B-Q4_K_M-GGUF-GGUF \
Agents-A1-4B-Q4_K_M.gguf --local-dir .
$ llama-cli -m Agents-A1-4B-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/agents-a1-4b-q4-k-m-gguf
{
"hf_id": "InternScience/Agents-A1-4B-Q4_K_M-GGUF",
"params_b": 4.00,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 184591,
"vram_estimates": [
{ "quant": "Q4_K_M", "gb": 4.1 },
{ "quant": "GGUF", "gb": 1.8 }
],
"updated_at": "2026-09-24T01:00:21Z"
}
Specifications
- Parameters
- 4.0 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-07-13
- Base model
- Agents-A1-4B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-24
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model