Gemma 3 12B IT
12BGoogle Gemma 3
Mid-size Gemma 3 with vision. Fits 16GB at Q4; excellent multilingual chat.
131K
Max Context
3
Quant Variants
GGUF Q5_K_M
Best Quality
+1.3%
Perplexity rise (best build)
Quantization Variants
Per-quant VRAM, quality loss, and inference speed on RTX 4090
Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports
| Format | Level | BPW | VRAM | PPL Loss | Speed | Source | Actions |
|---|---|---|---|---|---|---|---|
| GGUF | Q4_K_M | 4.85 | 8.5 GB | 2.9% | 105 tok/s | Estimated | |
| GGUF | Q5_K_M | 5.68 | 9.8 GB | 1.3% | 92 tok/s | Estimated | |
| AWQ | INT4 | 4 | 7.2 GB | 3.9% | 128 tok/s | Estimated |
Which file each size is for
A file size is not a memory figure: the VRAM column is the calculator's total at 4K context — weights plus KV cache plus a 10% activation buffer. Units differ on purpose: file sizes are decimal GB, as Hugging Face lists them; the VRAM column is GiB (1024³ bytes) with 2% added to the weights, so 7.12 GB of file counts as about 6.8 GiB there. A vision projector (mmproj), where the repo ships one, is a separate download and is in neither number.
- GGUF Q4_K_MSized at the calculator's generic rate for this level; no file was checked.
- GGUF Q5_K_MSized at the calculator's generic rate for this level; no file was checked.
- AWQ INT4Sized at the calculator's generic rate for this level; no file was checked.
Similar models
Compare with Gemma 3Gemma 3 4B IT
Google Gemma 3
Google Gemma 3 multimodal 4B. 128K context; strong vision + text on 8GB cards.
Gemma 3 27B IT
Google Gemma 3
Gemma 3 large instruct with long context and multimodal support. At Q4_K_M it needs about 18.3 GB at 4K, comfortable on a 24 GB card. The vision encoder is a separate 0.9 GB file.
Qwen3-VL 8B Instruct
Alibaba Qwen3-VL
Current-generation vision-language model that still fits a single 8–12GB card at Q4 (~5.9GB). The realistic multimodal option for people without a 24GB GPU — note the vision encoder adds VRAM the KV-cache math below does not model.
Qwen3.5 9B
Alibaba Qwen3.5
The newest small Qwen and a common pick for 8 to 16 GB cards. Only 8 of its 32 layers keep a growing KV cache, so it can use a long context on modest hardware. At Q4_K_M it needs about 6.6 GB at 4K and 7.0 GB at 16K, comfortable on an 8 GB card; at 32K (7.5 GB) it is tight there and comfortable from 10 GB up. Its full 256K window needs about 15.2 GB. Q8_0 needs about 10.4 GB, comfortable from 12 GB up. Reasoning is off by default on the small Qwen3.5 sizes, and it reads images through a separate vision encoder. Sizes come from the published GGUF file sizes, and no per-level quality loss has been published.
Running Gemma 3 12B IT locally
At Q4_K_M and 4K of context, Gemma 3 12B IT needs about 8.5 GB — 7.0 GB of weights, 0.72 GB of KV cache and a 0.8 GB activation buffer. The smallest cards in this index that clear that comfortably are 10 GB ones — 2 of them, from the Arc B570 10G up — and 67 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.
What longer context costs
Going from 4K to 32K adds about 1.75 GB, taking the total to 10.4 GB. That is gentler than the parameter count suggests: only 8 of 48 layers keep a KV cache that grows with context, and 40 more cap theirs at a sliding window, so the cache scales at a fraction of the usual rate. The model's native window is 128K; holding all of it at Q4_K_M would need about 17 GB.
Which build to download
This index tracks 2 formats for it — GGUF, AWQ — across 3 levels. Q5_K_M carries the lowest published perplexity loss at 1.3%. The fastest level listed is AWQ INT4 at about 128 tok/s on an RTX 4090, batch 1 — an estimate, not a run on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.
Common questions
- How much VRAM does Gemma 3 12B IT need?
- About 8.5 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 10.4 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
- Will Gemma 3 12B IT run on a 10GB GPU?
- Yes — at Q4_K_M and 4K context it needs about 8.5 GB, which leaves 1.5 GB spare on a Arc B570 10G, or on any of the other 10 GB cards here (2 in all). That is the smallest size in this index that clears it comfortably; 67 of 78 do.
- Which quantization of Gemma 3 12B IT should I use?
- Q5_K_M has the lowest published quality loss (1.3%), and Q4_K_M is the level most people run. All 3 levels in the index are Q4_K_M, Q5_K_M, AWQ INT4.
Where this model fits
Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.
- Runs comfortably on
- Arc B570 10G10GB · +1.5RTX 3080 10G10GB · +1.5RTX 3060 12G12GB · +3.5Radeon RX 6700 XT12GB · +3.5Radeon RX 7700 XT12GB · +3.5
- Just misses
- RTX 4060+0.5GB overRTX 4060 Ti 8G+0.5GB over
- Compared here
- GGUF vs AWQ
- A top pick for
- Best local LLM for 12GB
- Try it yourself
- Size it in the calculatorGenerate the run command
How to actually run this
Deployment guides for this model and this class of hardware.
This page's figures change when the model or the runtime does.Last updated 2026-11-11 RSS → /feed.xml