gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF
> No matter your GPU. No matter your RAM. With ~4.5 GB of VRAM or unified memory free, you can run your own > private, offline coding agent right now. 🚀 v2 is the big agentic upgrade — it reads, reasons, uses tools, > and works through multi-step technical tasks before it acts. 🧠🛠️ All local, all yours, no API, no cloud.
Params
—
Context
—
Downloads 30d
373 K
Likes
1,380
Download history
daily snapshots · 10 days429 K373 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 |
|---|---|---|---|---|
| gemma-4-12B-it-MTP-BF16.gguf | GGUF | 0.9 GB | 1.4 GB | ✅ Runs comfortably |
| gemma4-v2-Q3_K_M.gguf | Q3_K_M | 6.1 GB | 7.2 GB | ✅ Runs comfortably |
| gemma4-v2-Q4_K_M.gguf | Q4_K_M | 7.4 GB | 8.6 GB | ✅ Runs comfortably |
| gemma4-v2-Q6_K.gguf | Q6_K | 9.8 GB | 11.3 GB | ✅ Runs comfortably |
| gemma4-v2-Q8_0.gguf | Q8_0 | 12.7 GB | 14.4 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 gemma-4-12b-agentic-fable5-composer2-5-v2-3-5x-tau2-gguf # pin the quantization explicitly $ ollama run gemma-4-12b-agentic-fable5-composer2-5-v2-3-5x-tau2-gguf-q4_k_m
$ huggingface-cli download yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF-GGUF \
gemma4-v2-Q4_K_M.gguf --local-dir .
$ llama-cli -m gemma4-v2-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/gemma-4-12b-agentic-fable5-composer2-5-v2-3-5x-tau2-gguf
{
"hf_id": "yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 372914,
"vram_estimates": [
{ "quant": "GGUF", "gb": 1.4 },
{ "quant": "Q8_0", "gb": 14.4 }
],
"updated_at": "2026-07-28T18:05:36Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2026-06-19
- 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.