Mellum2-12B-A2.5B-Instruct-GGUF-Q8_0
This repository contains a GGUF Q80 quantization of JetBrains/Mellum2-12B-A2.5B-Instruct, ready to run with llama.cpp, Ollama, LM Studio, and other GGUF-compatible runtimes.
Params
—
Context
—
Downloads 30d
238 K
Likes
7
Download history
daily snapshots · 18 days242 K186 K
Sep 4Sep 10Sep 16Sep 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 |
|---|---|---|---|---|
| Mellum2-12B-A2.5B-Instruct-Q8_0.gguf | Q8_0 | 12.9 GB | 14.7 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 mellum2-12b-a2-5b-instruct-gguf-q8-0 # pin the quantization explicitly $ ollama run mellum2-12b-a2-5b-instruct-gguf-q8-0-q8_0
$ huggingface-cli download JetBrains/Mellum2-12B-A2.5B-Instruct-GGUF-Q8_0-GGUF \
Mellum2-12B-A2.5B-Instruct-Q8_0.gguf --local-dir .
$ llama-cli -m Mellum2-12B-A2.5B-Instruct-Q8_0.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/mellum2-12b-a2-5b-instruct-gguf-q8-0
{
"hf_id": "JetBrains/Mellum2-12B-A2.5B-Instruct-GGUF-Q8_0",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 238119,
"vram_estimates": [
{ "quant": "Q8_0", "gb": 14.7 }
],
"updated_at": "2026-09-04T01:00:31Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2026-06-04
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-04
Compare with any text-generation model