Search public pages, research tools, and SAVRN solutions.
Run with https://llama.app - https://huggingface.co/google/gemma-4-12B-it - https://huggingface.co/google/gemma-4-12B-it-assistant - https://huggingface.co/google/gemma-4-12B-it-qat-q40-unquantized-assistant …
By GGML Org, published under apache-2.0, revision e3e681731089.
Run with https://llama.app - https://huggingface.co/google/gemma-4-12B-it - https://huggingface.co/google/gemma-4-12B-it-assistant - https://huggingface.co/google/gemma-4-12B-it-qat-q40-unquantized-assistant - https://huggingface.co/google/gemma-4-12B-it-qat-q40-unquantized - add info - add dflash
Run with https://llama.app
llama serve -hf ggml-org/gemma-4-12B-it-GGUF
[!IMPORTANT] This model is automatically converted using https://github.com/ggml-org/convert
12 files, 45.6 GB in total. The weights are 8 files totalling 45.6 GB in gguf.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| gemma-4-12B-it-BF16.gguf | Weights | 23.8 GB | 2851bc5b1a24 |
| gemma-4-12B-it-Q4_0.gguf | Weights | 7.2 GB | 3712b9bd32ca |
| gemma-4-12B-it-Q8_0.gguf | Weights | 12.7 GB | abfc3044b937 |
| mmproj-gemma-4-12B-it-BF16.gguf | Weights | 175.1 MB | 9b1edfa05b63 |
| mmproj-gemma-4-12B-it-Q8_0.gguf | Weights | 159.0 MB | 59e62255435d |
| mtp-gemma-4-12B-it-BF16.gguf | Weights | 861.5 MB | 9b67d8e3650f |
| mtp-gemma-4-12B-it-Q4_0.gguf | Weights | 253.7 MB | b894e614824d |
| mtp-gemma-4-12B-it-Q8_0.gguf | Weights | 465.1 MB | 16c90eb9f2b2 |
| README.md | Documentation | 621 B | — |
| convert.log | Other | 439.2 KB | — |
| .gitattributes | Repository | 2.2 KB | — |
| .src_sha | Repository | 212 B | — |
Released by GGML Org through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 45.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Yes. gemma-4-12B-it-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Run with https://llama.app - https://huggingface.co/google/gemma-4-E4B-it - https://huggingface.co/google/gemma-4-E4B-it-assistant - https://huggingface.co/google/gemma-4-E4B-it-qat-q40-unquantized-assistant - https://huggingface.co/google/gemma-4-E4B-it-qat-q40-unquantized - add info - add dflash
This model ships a Multi-Token Prediction drafter at the repo root (mtp-gemma-4-12B-it.gguf, a near-lossless smart Q40). A recent llama.cpp auto-discovers it from -hf, so you do not pass --model-draft: The drafter shares the target's KV cache and does not change the output (the target verifies every drafted token). See the MTP/ folder for the other precisions and explicit usage. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context…
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in five distinct sizes: E2B, E4B, 12B, 26B A4B, and 31B. Their diverse sizes make them deployable in environments ranging from…
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in five distinct sizes: E2B, E4B, 12B, 26B A4B, and 31B. Their diverse sizes make them deployable in environments ranging from…
This model ships a Multi-Token Prediction drafter at the repo root (mtp-gemma-4-E4B-it.gguf, a near-lossless smart Q40). A recent llama.cpp auto-discovers it from -hf, so you do not pass --model-draft: The drafter shares the target's KV cache and does not change the output (the target verifies every drafted token). See the MTP/ folder for the other precisions and explicit usage. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context…
This model ships a Multi-Token Prediction drafter at the repo root (mtp-gemma-4-E2B-it.gguf, a near-lossless smart Q40). A recent llama.cpp auto-discovers it from -hf, so you do not pass --model-draft: The drafter shares the target's KV cache and does not change the output (the target verifies every drafted token). See the MTP/ folder for the other precisions and explicit usage. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context…