Gemma 3 1B IT VRAM & Memory Requirements

Memory layers in this estimate

Artifact bytes, raw KV, engine extras, and total demand are separate. This is not a runtime trace.

Weight artifact

0.93 GiB (1,003,541,152 bytes)

Raw KV cache

0.04 GiB (45,088,768 bytes)

Engine extras / workspace

0.13 GiB–0.52 GiB

Total estimated demand

1.10 GiB–1.50 GiB

Published artifacts

Memory by quantization and context

Concurrent sequences = 1. KV defaults to FP16. The range includes documented runtime extras for the listed engine. These figures use the same core as the interactive calculator.

Raw KV contribution

Related pages

• KV cache calculator
• 4-bit, 8-bit, and FP16 memory
• File size is not runtime VRAM
• Methodology
• All can-i-run checks

Sources

• Gemma 3 model card (Google AI for Developers) — Input context 128K tokens for 4B, 12B, 27B and 32K for 1B; images encoded to 256 tokens each. License: Gemma Terms of Use.
• Google gemma_pytorch config.py (architecture) — get_config_for_1b: num_hidden_layers=26, num_attention_heads=4, num_key_value_heads=1, hidden_size=1152, head_dim=256, sliding_window_size=512, attn_types = 5 LOCAL_SLIDING then 1 GLOBAL, cycled by layer index (gemma/model.py: attn_types[i % len(attn_types)]), so 4 global and 22 sliding layers. The Hugging Face config.json is gated (HTTP 401), so it was not read.
• Cross-check only: llama.cpp org GGUF header converted from Google's config (not an official Google source) — Header read with an HTTP range request on 2026-10-18: block_count 26, head_count 4, head_count_kv 1, embedding_length 1152, key_length 256, sliding_window 512, context_length 32768. All agree with gemma_pytorch config.py.
• Gemma releases — March 10, 2025: release of Gemma 3 in 1B, 4B, 12B and 27B sizes.
• Hugging Face API (BF16) — sha dcc83ea841ab6100d6b47a070329e1ba4cf78752; gated manual; safetensors.total=999885952; 1 safetensors siblings.
• Hugging Face API (QAT Q4_0 GGUF) — sha d1be121d36172a4b0b964657e2ee859d61138593; gemma-3-1b-it-q4_0.gguf = 1,003,541,152 bytes.

Assumptions that affect this result

• Requested context is within the recorded native window of 32768 tokens.
• Full-resident weight estimates use total parameters, including inactive MoE experts.
• Weight bytes come from the selected weight files only, not from every file in the repository.
• Download file size is not peak GPU memory. Runtime layout, allocator padding, and KV are extra.
• Counted files: gemma-3-1b-it-q4_0.gguf.
• Context budget is the number of cached tokens per sequence (prompt plus reserved generation).
• Concurrent sequences share one model replica; weights are not multiplied by sequence count.
• KV dtype is independent of weight quantization unless you change it.

Calculator