Google
Gemma 4 31B It
Gemma 4 31B It is an open-weights 31B-parameter model by Google. It holds an Intelligence score of 66.2 on the local.ai leaderboard (2026-08 snapshot).
open weights
66.2
local.ai Intelligence
Parameters
31B
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2026-07-20
Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.
Does it fit your hardware?
Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.
Q4_K_M 18GQ6_K 27.9GQ8_0 34.1GFP16 62G| Quantization | ≈ File size | Note |
|---|---|---|
| IQ2_XXS | 8.4 GB | Extreme compression, largest quality loss |
| IQ3_XXS | 11.2 GB | Very small |
| Q3_K_M | 14.3 GB | Small |
| NVFP4 | 15.5 GB | NVIDIA 4-bit |
| Q4_K_S | 16.7 GB | Common |
| Q4_K_M | 18 GB | Most common sweet spot |
| Q5_K_M | 23.6 GB | Balanced |
| Q6_K | 27.9 GB | Near-lossless |
| Q8_0 | 34.1 GB | Near-lossless |
| FP16 | 62 GB | Original weights |
Actual files on HuggingFace
| File | Size |
|---|---|
| model-00001-of-00002.safetensors | 46.37 GB |
| model-00002-of-00002.safetensors | 11.89 GB |
GGUF: unsloth/gemma-4-31B-it-GGUF · 549,239 downloads
| File | Size | |
|---|---|---|
| BF16/gemma-4-31B-it-BF16-00001-of-00002.gguf | 46.52 GB | download |
| BF16/gemma-4-31B-it-BF16-00002-of-00002.gguf | 10.68 GB | download |
| MTP/mtp-gemma-4-31B-it-BF16.gguf | 0.89 GB | download |
| MTP/mtp-gemma-4-31B-it-F16.gguf | 0.89 GB | download |
| MTP/mtp-gemma-4-31B-it-Q8_0.gguf | 0.48 GB | download |
| gemma-4-31B-it-IQ4_NL.gguf | 16.10 GB | download |
| gemma-4-31B-it-IQ4_XS.gguf | 15.25 GB | download |
| gemma-4-31B-it-Q3_K_M.gguf | 13.72 GB | download |
| gemma-4-31B-it-Q3_K_S.gguf | 12.30 GB | download |
| gemma-4-31B-it-Q4_0.gguf | 16.15 GB | download |
| gemma-4-31B-it-Q4_1.gguf | 17.81 GB | download |
| gemma-4-31B-it-Q4_K_M.gguf | 17.07 GB | download |
GGUF: unsloth/gemma-4-31B-it-qat-GGUF · 312,475 downloads
| File | Size | |
|---|---|---|
| MTP/mtp-gemma-4-31B-it-BF16.gguf | 0.89 GB | download |
| MTP/mtp-gemma-4-31B-it-F16.gguf | 0.89 GB | download |
| MTP/mtp-gemma-4-31B-it-Q4_0.gguf | 0.26 GB | download |
| MTP/mtp-gemma-4-31B-it-Q8_0.gguf | 0.48 GB | download |
| gemma-4-31B-it-qat-UD-Q4_K_XL.gguf | 16.10 GB | download |
| mmproj-BF16.gguf | 1.12 GB | download |
| mmproj-F16.gguf | 1.12 GB | download |
| mmproj-F32.gguf | 2.14 GB | download |
| mtp-gemma-4-31B-it.gguf | 0.26 GB | download |
What you save self-hosting this model
Uses the model's own API price when it exists; otherwise the closest commercial equivalent.
Waiting for hardware detection…
RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.