Spark-X2.5-4B-GGUF
Spark-X2.5 is a compact, general-purpose language model for conversation, writing, translation, reasoning, coding, tool use, and agentic workflows. It uses a hybrid attention architecture, supports a native context length of up to 1M tokens, and covers more than 200 languages. For its architecture, training methods, benchmark results, fine-tuning, and citation, see the Spark-X2.5-4B.
Params
4.0 B
Context
—
Downloads 30d
315 K
Likes
289
Download history
daily snapshots · 54 days
▲ 180 K in the last 30 days (36.4%)
495 K315 K
Oct 12Oct 22Nov 1Nov 10
496 K207 K
Sep 18Oct 6Oct 24Nov 10
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 |
|---|---|---|---|---|
| Spark-X2.5-4B-Q4_K_M.gguf | Q4_K_M | 2.6 GB | 4.0 GB | ✅ Runs comfortably |
| Spark-X2.5-4B-Q8_0.gguf | Q8_0 | 4.4 GB | 5.9 GB | ✅ Runs comfortably |
| Spark-X2.5-4B.gguf | GGUF | 8.2 GB | 10.2 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 spark-x2-5-4b-gguf # pin the quantization explicitly $ ollama run spark-x2-5-4b-gguf-q4_k_m
$ huggingface-cli download XHToken/Spark-X2.5-4B-GGUF-GGUF \
Spark-X2.5-4B-Q4_K_M.gguf --local-dir .
$ llama-cli -m Spark-X2.5-4B-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/spark-x2-5-4b-gguf
{
"hf_id": "XHToken/Spark-X2.5-4B-GGUF",
"params_b": 4.00,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 315487,
"vram_estimates": [
{ "quant": "Q4_K_M", "gb": 4.0 },
{ "quant": "Q8_0", "gb": 5.9 }
],
"updated_at": "2026-09-21T01:00:13Z"
}
Specifications
- Parameters
- 4.0 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-08-28
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-18
Compare with any text-generation model