Downloads · 30 days
19
10% of all-time downloads
DeepGemma-2B-Reasoning-GGUF
Zhantas/DeepGemma-2B-Reasoning-GGUF
DeepGemma-2B-Reasoning-GGUF is a machine learning model from Zhantas. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.
This is the quantized GGUF version of Zhantas/DeepGemma-2B-Reasoning.
All-time downloads
199
Public
Repo size
3.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf3.4 GB · 100%
At a glance
- License
- gemma
- Access
- Public
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026
- SHA
- 0bd306ff
Base models
Model card
From the Hugging Face model README
🗜️ DeepGemma-2B-Reasoning — GGUF (Q4_K_M)
This is the quantized GGUF version of Zhantas/DeepGemma-2B-Reasoning.
For the full model, training details and benchmarks — see the original repo.
📦 File
| File | Size | Description |
|---|---|---|
gemma4_e2b-q4_k_m.gguf | ~4.7 GB | Q4_K_M quantization |
⚡ Performance (RTX 4090, llama.cpp, ngl=999)
| Metric | Speed |
|---|---|
| Prompt processing | ~400 tok/s |
| Generation | ~239–262 tok/s |
| Context | 4096 tokens |
💻 Usage
./llama-cli -m gemma4_e2b-q4_k_m.gguf \
-p "<start_of_turn>user\nYour question here<end_of_turn>\n<start_of_turn>model\n" \
-n 512 -ngl 999 -c 4096
⚠️ Limitations
Prone to "overthinking" on simple tasks. Best suited for logic puzzles, coding, and mathematics.
- License
- gemma
- Languages
- ru, en
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026