axteam/gemma-4-12B-it-FP8-dynamic
Image-Text-to-Text • 12B • Updated • 15
Gemma4
axteam's Gemma 4 quantizations — FP8 dynamic, AWQ INT4/INT8, NVFP4 (W4A4 & W4A16), and GGUF — for 12B-it, E4B-it, 26B-A4B(+it), 31B(+it).
Note gemma-4-12B-it · FP8 dynamic (W8A8) — near-lossless; Hopper/Ada/Blackwell
axteam/gemma-4-12B-it-AWQ-8bit
Image-Text-to-Text • 12B • Updated • 13Note gemma-4-12B-it · AWQ W8A16 INT8 — near-lossless
axteam/gemma-4-12B-it-AWQ-4bit
Image-Text-to-Text • 12B • Updated • 11Note gemma-4-12B-it · AWQ W4A16 INT4 — ~1/4 size
axteam/gemma-4-12B-it-NVFP4A16
Image-Text-to-Text • 12B • Updated • 14Note gemma-4-12B-it · NVFP4 W4A16 (FP4 weights, BF16 activations) — best 4-bit quality
axteam/gemma-4-12B-it-NVFP4
Image-Text-to-Text • 12B • Updated • 12Note gemma-4-12B-it · NVFP4 W4A4 (FP4 weights + activations) — fastest on Blackwell
axteam/gemma-4-12B-it-GGUF
Image-Text-to-Text • 12B • Updated • 76Note gemma-4-12B-it · GGUF (Q4_K_M / Q8_0 / BF16) for llama.cpp / Ollama
axteam/gemma-4-E4B-it-FP8-dynamic
Image-Text-to-Text • 8B • Updated • 14Note gemma-4-E4B-it · FP8 dynamic (W8A8) — near-lossless; Hopper/Ada/Blackwell
axteam/gemma-4-E4B-it-AWQ-8bit
Image-Text-to-Text • 8B • Updated • 14Note gemma-4-E4B-it · AWQ W8A16 INT8 — near-lossless
axteam/gemma-4-E4B-it-AWQ-4bit
Image-Text-to-Text • 8B • Updated • 17Note gemma-4-E4B-it · AWQ W4A16 INT4 — ~1/4 size
axteam/gemma-4-E4B-it-NVFP4A16
Image-Text-to-Text • 8B • Updated • 15Note gemma-4-E4B-it · NVFP4 W4A16 (FP4 weights, BF16 activations) — best 4-bit quality
axteam/gemma-4-E4B-it-NVFP4
Image-Text-to-Text • 8B • Updated • 13Note gemma-4-E4B-it · NVFP4 W4A4 (FP4 weights + activations) — fastest on Blackwell
axteam/gemma-4-E4B-it-GGUF
Image-Text-to-Text • 8B • Updated • 84Note gemma-4-E4B-it · GGUF (Q4_K_M / Q8_0 / BF16) for llama.cpp / Ollama
axteam/gemma-4-26B-A4B-FP8-dynamic
Image-Text-to-Text • 26B • Updated • 18Note gemma-4-26B-A4B · FP8 dynamic (W8A8) — near-lossless; Hopper/Ada/Blackwell
axteam/gemma-4-26B-A4B-AWQ-8bit
Image-Text-to-Text • 9B • Updated • 16Note gemma-4-26B-A4B · AWQ W8A16 INT8 — near-lossless
axteam/gemma-4-26B-A4B-AWQ-4bit
Image-Text-to-Text • 26B • Updated • 19Note gemma-4-26B-A4B · AWQ W4A16 INT4 — ~1/4 size
axteam/gemma-4-26B-A4B-NVFP4A16
Image-Text-to-Text • 26B • Updated • 1Note gemma-4-26B-A4B · NVFP4 W4A16 (FP4 weights, BF16 activations) — best 4-bit quality
axteam/gemma-4-26B-A4B-NVFP4
Image-Text-to-Text • 26B • Updated • 17Note gemma-4-26B-A4B · NVFP4 W4A4 (FP4 weights + activations) — fastest on Blackwell
axteam/gemma-4-26B-A4B-GGUF
Image-Text-to-Text • 25B • Updated • 56Note gemma-4-26B-A4B · GGUF (Q4_K_M / Q8_0 / BF16) for llama.cpp / Ollama
axteam/gemma-4-26B-A4B-it-FP8-dynamic
Image-Text-to-Text • 26B • Updated • 28Note gemma-4-26B-A4B-it · FP8 dynamic (W8A8) — near-lossless; Hopper/Ada/Blackwell
axteam/gemma-4-26B-A4B-it-AWQ-8bit
Image-Text-to-Text • 9B • Updated • 13Note gemma-4-26B-A4B-it · AWQ W8A16 INT8 — near-lossless
axteam/gemma-4-26B-A4B-it-AWQ-4bit
Image-Text-to-Text • 26B • Updated • 26Note gemma-4-26B-A4B-it · AWQ W4A16 INT4 — ~1/4 size
axteam/gemma-4-26B-A4B-it-NVFP4A16
Image-Text-to-Text • 26B • Updated • 4Note gemma-4-26B-A4B-it · NVFP4 W4A16 (FP4 weights, BF16 activations) — best 4-bit quality
axteam/gemma-4-26B-A4B-it-NVFP4
Image-Text-to-Text • 26B • Updated • 20Note gemma-4-26B-A4B-it · NVFP4 W4A4 (FP4 weights + activations) — fastest on Blackwell
axteam/gemma-4-26B-A4B-it-GGUF
Image-Text-to-Text • 25B • Updated • 87Note gemma-4-26B-A4B-it · GGUF (Q4_K_M / Q8_0 / BF16) for llama.cpp / Ollama
axteam/gemma-4-31B-FP8-dynamic
Image-Text-to-Text • 31B • Updated • 18Note gemma-4-31B · FP8 dynamic (W8A8) — near-lossless; Hopper/Ada/Blackwell
axteam/gemma-4-31B-AWQ-8bit
Image-Text-to-Text • 10B • Updated • 14Note gemma-4-31B · AWQ W8A16 INT8 — near-lossless
axteam/gemma-4-31B-AWQ-4bit
Image-Text-to-Text • 7B • Updated • 18Note gemma-4-31B · AWQ W4A16 INT4 — ~1/4 size
axteam/gemma-4-31B-NVFP4A16
Image-Text-to-Text • 18B • Updated • 8Note gemma-4-31B · NVFP4 W4A16 (FP4 weights, BF16 activations) — best 4-bit quality
axteam/gemma-4-31B-NVFP4
Image-Text-to-Text • 18B • Updated • 9Note gemma-4-31B · NVFP4 W4A4 (FP4 weights + activations) — fastest on Blackwell
axteam/gemma-4-31B-GGUF
Image-Text-to-Text • 31B • Updated • 52Note gemma-4-31B · GGUF (Q4_K_M / Q8_0 / BF16) for llama.cpp / Ollama
axteam/gemma-4-31B-it-FP8-dynamic
Image-Text-to-Text • 31B • Updated • 21Note gemma-4-31B-it · FP8 dynamic (W8A8) — near-lossless; Hopper/Ada/Blackwell
axteam/gemma-4-31B-it-AWQ-8bit
Image-Text-to-Text • 10B • Updated • 16Note gemma-4-31B-it · AWQ W8A16 INT8 — near-lossless
axteam/gemma-4-31B-it-AWQ-4bit
Image-Text-to-Text • 7B • Updated • 21Note gemma-4-31B-it · AWQ W4A16 INT4 — ~1/4 size
axteam/gemma-4-31B-it-NVFP4A16
Image-Text-to-Text • 18B • Updated • 8Note gemma-4-31B-it · NVFP4 W4A16 (FP4 weights, BF16 activations) — best 4-bit quality
axteam/gemma-4-31B-it-NVFP4
Image-Text-to-Text • 18B • Updated • 22 • 2Note gemma-4-31B-it · NVFP4 W4A4 (FP4 weights + activations) — fastest on Blackwell
axteam/gemma-4-31B-it-GGUF
Image-Text-to-Text • 31B • Updated • 83Note gemma-4-31B-it · GGUF (Q4_K_M / Q8_0 / BF16) for llama.cpp / Ollama
axteam/gemma-4-E2B-it-GGUF
Image-Text-to-Text • 5B • UpdatedNote gemma-4-E2B-it · GGUF (Q4_K_M / Q8_0 / BF16) for llama.cpp / Ollama