gemma 4

5 articles · newest first

Editorial infographic of a mixture-of-experts model: a few active expert blocks on a GPU and the rest resting in system memory, near-black background, indigo-violet with a coral accent

Gemma 4 26B-A4B locally: the Gemma that runs fast on 16GB

Gemma 4's mixture-of-experts model holds about 26B parameters but activates only 3.8B — so it's quick, and it fits a 16GB card at Q4. The VRAM math, the GPU, and the run command.

Tensor · Sep 26 · 7 min

Realistic painterly illustration of a large glowing processor die radiating soft light on a dark surface, deep indigo-violet with a warm coral highlight

Gemma 4 31B locally: the 24GB-card Gemma

Gemma 4 31B is the big dense Gemma — the one that asks for a 24GB card and rewards it. The VRAM per quant, the GPU that fits, and how to run it without pulling the wrong tag.

Tensor · Sep 26 · 7 min

Isometric diorama of a friendly glowing AI chip seated on a mid-range graphics card, near-black background, indigo-violet with a coral accent

Gemma 4 12B locally: the VRAM, the GPU, and one Ollama gotcha

Google's Gemma 4 12B is the multimodal open model that fits a mid-range card — if you pull the right Ollama tag. The honest VRAM math, the cheapest GPU that runs it, and how to start.

Tensor · Sep 26 · 7 min

Flat illustration of a person choosing between small, medium and large boxes to fit into a slot on a graphics card, a small robot helper watching

Agents

Run OpenClaw or Hermes on a local model: which fits your GPU

Ollama's default gemma4 is the small E4B and qwen3.5 is the 9B, not what most people assume. What each tag really downloads, what the bigger models need at the 64K context agents use, and what to pick for 12, 16 and 24GB cards.

Tensor · Sep 25 · 7 min

Ollama, the local-model runtime used to run open-weight LLMs on consumer GPUs

a free model on your 24GB GPU codes within 4 points of Claude Opus. meet Qwen3.6-27B

on a single 24GB card in 2026 there's no one 'best' — it's a clean three-way split: Qwen3.6-27B for coding, Gemma 4 for vision, gpt-oss-20b for raw speed. and a used RTX 3090 still competes, because this is a memory game, not a compute one.

Tensor · Jul 19 · 7 min