Yes — with 189.2 GB to spare
Gemma 3 1B at Q4_K_M fits your Instinct MI300X entirely on the GPU at 8K context, at an estimated 5706 tokens per second. There is room for its full 32K window.
Text-only. Single KV head makes its cache almost free at long context.
Hardware requirements What hardware do I need to run Gemma 3 1B? →At Q4_K_M with an 8K context: a 6 GB GPU (RTX 3060 Laptop) or a 8 GB Mac (M3). 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 | 1.9 GB | 2.5 GB | 32K | 1723 | Reference | Long context |
| Q8_0 | 1.0 GB | 1.6 GB | 32K | 3242 | −0.1% ppl | Long context |
| Q6_K | 0.8 GB | 1.4 GB | 32K | 4201 | −0.4% ppl | Long context |
| Q5_K_M | 0.7 GB | 1.3 GB | 32K | 4861 | −0.8% ppl | Long context |
| Q4_K_M | 0.6 GB | 1.2 GB | 32K | 5706 | −1.9% ppl | Recommended |
| Q3_K_M | 0.5 GB | 1.1 GB | 32K | 7049 | −5.4% ppl | Long context |
| Q2_K | 0.4 GB | 1.0 GB | 32K | 8227 | −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 (512 tokens, 1 global in 6), which is why its cache barely grows with context.
How to run it
$ ollama pull gemma3:1b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run gemma3:1b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
Related models on an Instinct MI300X
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Gemma 3 4B 4.3B · same family |
Q4_K_M · 3.3 GB | 1327 | Runs great |
| Gemma 3 12B 12.2B · same family |
Q4_K_M · 8.3 GB | 468 | Runs great |
| Gemma 3 27B 27.4B · same family |
Q4_K_M · 17.0 GB | 208 | Runs great |
| Qwen3.5 0.8B 0.87B · similar size |
Q4_K_M · 1.2 GB | 6559 | Runs great |
| Llama 3.2 1B Instruct 1.24B · similar size |
Q4_K_M · 1.5 GB | 4602 | Runs great |
| Qwen3 0.6B 0.6B · similar size |
Q4_K_M · 1.8 GB | 9510 | Runs great |
| Qwen3 1.7B 1.72B · similar size |
Q4_K_M · 2.4 GB | 3317 | Runs great |
Gemma 3 1B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 3060 Laptop 5.3 GB usable · 336 GB/s |
1.2 GB | 362 | Runs great |
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
1.2 GB | 276 | Runs great |
| M3 · 8 GB 5.4 GB usable · 100 GB/s |
1.2 GB | 99 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
1.2 GB | 388 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
1.2 GB | 119 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
1.2 GB | 1085 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
1.2 GB | 1034 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
1.2 GB | 398 | Runs great |