Downloads · 30 days
38
43% of all-time downloads
Gemma_4_Gem_e4b_multimodal-NF4
stamsam/Gemma_4_Gem_e4b_multimodal-NF4
Gemma_4_Gem_e4b_multimodal-NF4 is a image-text-to-text model from stamsam. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
<div align="center"<img src="Gem%20e4b.png" alt="Gemma 4 Gem E4B" width="80%"<br<br<bFormat: 4-bit NF4</b | <bBase: google/gemma-4-E4B-it</b | <b4.5B effective / ~8B incl. embeddings</b</div
All-time downloads
88
Public
Parameters
6B
10 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10 GB · 100%
Parameter types
How the weights are stored.
BF164B · 66%
Try a prompt
Base models
Model card
From the Hugging Face model README
<div align="center"><img src="Gem%20e4b.png" alt="Gemma 4 Gem E4B" width="80%"><br><br><b>Format: 4-bit NF4</b> | <b>Base: google/gemma-4-E4B-it</b> | <b>4.5B effective / ~8B incl. embeddings</b></div>
Gemma 4 Gem E4B Multimodal
A fine-tuned version of google/gemma-4-E4B-it optimized for local coding, tool use, instruction following, and structured output. Trained on an H100 via 5-stage distillation pipeline (SFT + DPO + HF curriculum augmentation).
Hard fails reduced by 76% vs stock E4B (17 → 4 on full40 benchmark).
Model Details
This model includes the original vision and audio encoders from google/gemma-4-E4B-it, allowing it to process images, audio, and text inputs. The text backbone has been fine-tuned; vision/audio encoders are from the base model.
| Property | Value |
|---|---|
| Base Model | google/gemma-4-E4B-it (4.5B effective / ~8B incl. embeddings) |
| Training | 5-stage CUDA pipeline (SFT → DPO → HF Curriculum) |
| Quantization | 4-bit NF4 (bitsandbytes) — full BF16 base on request |
| Context | 2048 tokens |
| Format | ChatML-style with `< |
Training Datasets
- stage_elite_blend (1,920 rows) — Openthoughts/Hermes/XLam gold-standard reasoning
- Agentic CoT Coding SFT (429 rows) — Multi-step coding agent tasks
- Glaive Function Calling v2 (1,000 rows) — Tool-use and JSON schema compliance
Benchmark Results
Comparison against stock google/gemma-4-E4B-it (4-bit):
| Benchmark | Stock E4B | Gemma 4 Gem E4B | Improvement |
|---|---|---|---|
| full40 | 253/400 (6.33, 17 HF) | 259/400 (6.47, 4 HF) | +6 pts, -13 HF |
| code_smoke | — | 89/120 (7.42, 1 HF) | beats gate |
| json_hard | — | 30/30 (10.0, 0 HF) | perfect |
| false_premise_smoke | — | 87/110 (7.91, 0 HF) | clean |
| math_smoke | — | 41/60 (6.83, 0 HF) | clean |
Leaderboard Context
| Model | full40 | Hard Fails |
|---|---|---|
| Gemma 4 Gem E4B | 259 | 4 🏆 |
| Gemma 4 31B (cloud) | 261 | 15 |
| Chimera v4 (Gemma E2B) | 258 | 14 |
| Stock E4B (4-bit) | 253 | 17 |
| Granite 4.1 8B | 276 | 14 |
| Phi-4 Mini | 223 | 20 |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "stamsam/Gemma_4_Gem_e4b_multimodal_4-bit-NF4"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype="auto",
trust_remote_code=True,
)
messages = [{"role": "user", "content": "Write a function to deduplicate a list"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Training Details
- Hardware: NVIDIA H100 80GB SXM
- Framework: PyTorch 2.11 + PEFT + bitsandbytes 4-bit QLoRA
- LoRA config: r=8, alpha=16, target_modules=q/k/v/o/gate/up/down_proj
- Training time: ~30 minutes total across all stages
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma4
- License
- mit
- Languages
- en
- Created
- May 12, 2026
- Updated
- Aug 1, 2026