Yes — with 2.3 GB to spare
Gemma 3 12B at Q4_K_M fits your Arc B580 entirely on the GPU at 8K context, at an estimated 40 tokens per second. Past 45K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Strong multilingual chat with images, sized for 12–16 GB cards. Gemma 4 12B is the same size and better.
Hardware requirements What hardware do I need to run Gemma 3 12B? →At Q4_K_M with an 8K context: a 12 GB GPU (RTX 3060 12 GB) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 22.7 GB | 24.1 GB | — | ~2.5 | Reference | 13.5 GB over |
| Q8_0 | 12.1 GB | 13.5 GB | — | ~8.9 | −0.1% ppl | 2.9 GB over |
| Q6_K | 9.3 GB | 10.7 GB | 5K | ~27 | −0.4% ppl | 0.1 GB over |
| Q5_K_M | 8.1 GB | 9.5 GB | 26K | 34 | −0.8% ppl | Long context |
| Q4_K_M | 6.9 GB | 8.3 GB | 45K | 40 | −1.9% ppl | Recommended |
| Q3_K_M | 5.6 GB | 7.0 GB | 66K | 50 | −5.4% ppl | Long context |
| Q2_K | 4.8 GB | 6.2 GB | 78K | 58 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (1024 tokens, 1 global in 6), which is why its cache barely grows with context.
How to run it
$ ollama pull gemma3:12b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run gemma3:12b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
Related models on an Arc B580
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Gemma 3 27B 27.4B · same family |
Q4_K_M · 17.0 GB | ~4.8 | CPU offload |
| Gemma 3 4B 4.3B · same family |
Q4_K_M · 3.3 GB | 114 | Runs great |
| Gemma 3 1B 1.0B · same family |
Q4_K_M · 1.2 GB | 491 | Runs great |
| Mistral NeMo 12B 12.2B · similar size |
Q4_K_M · 8.7 GB | 40 | Runs great |
| Gemma 4 12B 12B · similar size |
Q4_K_M · 8.2 GB | 41 | Runs great |
| Ministral 3 14B 13.9B · similar size |
Q4_K_M · 9.7 GB | 35 | Tight fit |
| Phi-4 14B 14.7B · similar size |
Q4_K_M · 10.4 GB | 33 | Tight fit |
Gemma 3 12B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
8.3 GB | ~14 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
8.3 GB | 32 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
8.3 GB | 9.8 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
8.3 GB | 89 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
8.3 GB | 85 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
8.3 GB | 33 | Runs great |