unsloth
gemma 3 1b it
gemma 3 1b it is a 1.00B dense gemma3 model from unsloth. Configured context length is 32,768 tokens. License: gemma. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters1.0B
Context32K
Attentionhybrid
Licensegemma
26 layers · 1 KV heads · head dim 256 · 22 sliding layers · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| BF16 | 1.87 GB | Hugging Face file bytes |
| UD-Q8_K_XL | 1.38 GB | Hugging Face file bytes |
| Q8_0 | 1.00 GB | Hugging Face file bytes |
| UD-Q6_K_XL | 0.96 GB | Hugging Face file bytes |
| Q6_K | 0.94 GB | Hugging Face file bytes |
| UD-Q5_K_XL | 0.81 GB | Hugging Face file bytes |
| Q5_K_M | 0.79 GB | Hugging Face file bytes |
| Q5_K_S | 0.78 GB | Hugging Face file bytes |
| UD-Q4_K_XL | 0.75 GB | Hugging Face file bytes |
| Q4_K_M | 0.75 GB | Hugging Face file bytes |
| Q4_K_S | 0.73 GB | Hugging Face file bytes |
| IQ4_NL | 0.67 GB | Hugging Face file bytes |
| IQ4_XS | 0.67 GB | Hugging Face file bytes |
| Q4_1 | 0.71 GB | Hugging Face file bytes |
| Q4_0 | 0.67 GB | Hugging Face file bytes |
| UD-Q3_K_XL | 0.68 GB | Hugging Face file bytes |
| Q3_K_M | 0.67 GB | Hugging Face file bytes |
| Q3_K_S | 0.64 GB | Hugging Face file bytes |
| UD-IQ3_XXS | 0.55 GB | Hugging Face file bytes |
| UD-Q2_K_XL | 0.65 GB | Hugging Face file bytes |
| Q2_K | 1.28 GB | Hugging Face file bytes |
| UD-IQ2_XXS | 0.53 GB | Hugging Face file bytes |
| UD-IQ1_M | 0.52 GB | Hugging Face file bytes |
| UD-IQ1_S | 0.52 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Runs great | BF16 | 71–97 |
| GeForce RTX 3060 12GB | Runs great | BF16 | 89–121 |
| GeForce RTX 4060 Ti 16GB | Runs great | BF16 | 71–97 |
| GeForce RTX 4090 | Runs great | BF16 | 249–340 |
| GeForce RTX 5090 | Runs great | BF16 | 443–604 |
| Apple M4 Pro | Runs great | BF16 | 67–92 |
| Apple M5 | Runs great | BF16 | 38–52 |
| CPU only · DDR5-5600 | Runs on CPU | BF16 | 22–30 |
Smallest devices that fit it fully
- GeForce RTX 3050 6GB — Runs great, BF16, 42–57 tok/s
- GeForce RTX 2060 6GB — Runs great, BF16, 83–113 tok/s
- GeForce GTX 1660 Super — Runs great, BF16, 83–113 tok/s
- GeForce GTX 1660 Ti — Runs great, BF16, 71–97 tok/s
- Intel Arc A380 — Runs great, BF16, 46–63 tok/s
- GeForce RTX 5060 Ti 8GB — Runs great, BF16, 111–151 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (BF16).
llama.cpp
llama-server -hf unsloth/gemma-3-1b-it-GGUF:BF16 -c 8192 -ngl 26
Ollama
ollama run gemma
LM Studio
lms get unsloth/gemma-3-1b-it-GGUF # Then load quant BF16