bartowski / text-generation updated 2 years ago

gemma-2-2b-it-GGUF

Filename Quant type File Size Split Description -------- ---------- --------- ----- ----------- gemma-2-2b-it-f32.gguf f32 10.46GB false Full F32 weights. gemma-2-2b-it-Q80.gguf Q80 2.78GB false Extremely high quality, generally unneeded but max available quant. gemma-2-2b-it-Q6KL.gguf Q6KL 2.29GB false Uses Q80 for embed and output weights. Very high quality, near perfect, recommended. gemma-2-2b-it-Q6K.gguf Q6K 2.1...

Params
Context
Downloads 30d
158 K
Likes
100
Commercial use: conditional · gemma Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 56 days
▲ 0 in the last 30 days (0.0%)
158 K158 K
Jul 28Aug 15Sep 3Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
gemma-2-2b-it-IQ3_M.gguf IQ3_M 1.4 GB 2.0 GB ✅ Runs comfortably
gemma-2-2b-it-IQ4_XS.gguf IQ4_XS 1.6 GB 2.2 GB ✅ Runs comfortably
gemma-2-2b-it-Q3_K_L.gguf Q3_K_L 1.6 GB 2.2 GB ✅ Runs comfortably
gemma-2-2b-it-Q4_K_S.gguf Q4_K_S 1.6 GB 2.3 GB ✅ Runs comfortably
gemma-2-2b-it-Q4_K_M.gguf Q4_K_M 1.7 GB 2.4 GB ✅ Runs comfortably
gemma-2-2b-it-Q5_K_M.gguf Q5_K_M 1.9 GB 2.6 GB ✅ Runs comfortably
gemma-2-2b-it-Q5_K_S.gguf Q5_K_S 1.9 GB 2.6 GB ✅ Runs comfortably
gemma-2-2b-it-Q6_K.gguf Q6_K 2.2 GB 2.9 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · Q4_K_M
$ ollama run gemma-2-2b-it-gguf

# pin the quantization explicitly
$ ollama run gemma-2-2b-it-gguf-q4_k_m
est. VRAM 2.4 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
gemma
First seen on the Hub
2024-07-31
Base model
gemma-2-2b-it
Training datasets
undisclosed
Added to our catalog
2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-generation model