google/gemma-3-27b-it · Discussions

#108 opened 6 days ago by

chanduyadav023

Status on Gemma 4?

#107 opened 20 days ago by

Please open-source Gemini 1.0 Nano-1 (1.8B) 🙏

#106 opened about 1 month ago by

status on gemma 3.5?

#105 opened about 1 month ago by

Gemma 4 vs Qwen3.5 27b

#104 opened about 1 month ago by

EvilinaMaller

Add SWE-Bench Pro evaluation results

#103 opened about 2 months ago by

nielsr

Performance evaluation of Gemma 3-27b-it with different quantization methods (4-bit vs 8-bit)

#102 opened about 2 months ago by

Ryan1007

Please release now Gemma 3.5

#101 opened about 2 months ago by

Status on Gemma 4?

🔥 6

9

#100 opened 2 months ago by

Dampfinchen

Request: DOI

#99 opened 3 months ago by

Karthickweb7773

Request: DOI

#96 opened 5 months ago by

talha06

Config.json using illegal math, Echolabz will help you fix it..

#94 opened 5 months ago by

djkillerbee

ValueError: Number of images does not match number of special image tokens in the input text. Got 256 image tokens in the text but 256 tokens from image embeddings.

5

#91 opened 8 months ago by

zml31415

gemma-3-27b-it-FP8 sometimes crashes

#90 opened 8 months ago by

mondaylord

Support QLoRA Training on AWQ Quantized Models

#89 opened 8 months ago by

s3171103

Is there a minimum CUDA and/or BitsAndBytes version requirement?

#88 opened 8 months ago by

deathknight0

Update config file

#87 opened 9 months ago by

rishirath

therapeuticsgemma3

#86 opened 9 months ago by

mdordevic

Gemma 3 hyperparameters

#84 opened 9 months ago by

Augustas17

How Instructions, Tools and MCP terms are related

#83 opened 10 months ago by

jvoid

Model Parameters number vs Quantization level tradeoff

5

#82 opened 10 months ago by

jvoid

Suffix meaning IT vs PT

7

#81 opened 10 months ago by

jvoid

No output / Repeated outputs when using Gemma 3 12B/27B on vLLM

7

#79 opened 10 months ago by

sanchitahuja205

Genn

#78 opened 10 months ago by

ezelhan959

qwz

#77 opened 10 months ago by

Axdar

Specification

#76 opened 10 months ago by

zarifhaikal01

Too much VRAM in vLLM

#75 opened 11 months ago by

cbrug

Gemma-3-27B-it not loading on multi-GPU setup

#74 opened 11 months ago by

glawyer

Passing pictures as arrays to the model (Pytorch or Numpy)

#73 opened 11 months ago by

artyomboyko

Update config.json

#71 opened 11 months ago by

olegshulyakov

vllm and "gemma-3-27b-it" dont work

➕ 9

11

#70 opened 11 months ago by

nastyafairypro

How to eval the video/image sequences?

#69 opened 11 months ago by

lkllkl

Wrong context length limit for HuggingChat?

#68 opened 12 months ago by

vesjolovam

Undesired output texts

#67 opened 12 months ago by

Waisullah

Add reasoning capabilities for gemma 3

#66 opened 12 months ago by

devopsML

Getting 401 unaauthorized when trying to use google/gemma-3-27b-it

#65 opened 12 months ago by

Milinddurugkar

pad output?

#63 opened 12 months ago by

juniworld

Wrong answer by gemma3-27b-it : what is the difference betweem each: google/gemma-3-27b-it, google/gemma-3-27b-pt

#62 opened about 1 year ago by

Waisullah

Example of a wrong answer from an Image analysis

#61 opened about 1 year ago by

vince62s

Test using M1 Max (64G) and Word

#60 opened about 1 year ago by

gptlocalhost

what does "it" in the model name represent?

#59 opened about 1 year ago by

jdsouza

Update README.md

#58 opened about 1 year ago by

denizzhansahin

Gemma3ForCausalLM has no prepare_4d_causal_attention_mask_with_cache_position

#57 opened about 1 year ago by

buckeye17-bah

Inference speed slow?

👍 2

#56 opened about 1 year ago by

banank1989

Internal Server Error for url using vllm

#55 opened about 1 year ago by

panyupj

Could not find the transformer layer class SiglipMultiheadAttentionPoolingHead in the model.

👍 3

5

#54 opened about 1 year ago by

neilwu

Keeps repeating itself.

#53 opened about 1 year ago by

RealBiggly

Why MLP so tiny but vision part of the model works quite well

#52 opened about 1 year ago by

CCRss

Using google/gemma-3-4b-it as asssitant model for speculative decoding does not work

#51 opened about 1 year ago by

sayambhu

Update README.md