Ivan Baldo

ibaldonl's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in Qwen/Qwen3.8-27B 6 days ago

NVFP4 Shootout (Quality and Speed)

❤️➕ 7

10

#192 opened 22 days ago by

Rieker

New activity in Inferact/Qwen3.8-27B-NVFP4 23 days ago

Missing vLLM FP8 KVCache calibration

#3 opened 23 days ago by

ibaldonl

New activity in ISTA-DASLab/Qwen3.8-27B-3Bit-GSQ 27 days ago

Maybe add vLLM FP8 KVCache calibration scales?

4

#3 opened 28 days ago by

ibaldonl

New activity in TelperionAI/Qwen3.8-27B-INT4-AWQ-GPTQ-gdn4 28 days ago

FP8 vLLM KVCache calibration is missing

5

#2 opened 29 days ago by

ibaldonl

New activity in kaitchup/Qwen3.8-27B-hum-quality-MTP-19.2GB 28 days ago

Maybe add vLLM FP8 KVCache calibration scales

3

#2 opened 29 days ago by

ibaldonl

New activity in cyankiwi/Qwen3.8-27B-AWQ-INT4 29 days ago

vLLM KVCache FP8 calibration data missing

➕ 1

1

#7 opened 29 days ago by

ibaldonl

New activity in RedHatAI/Qwen3.8-27B-INT4 29 days ago

Doesn't have FP8 VLLM KVCache calibration scales

➕ 1

3

#3 opened 29 days ago by

ibaldonl

New activity in ISTA-DASLab/Qwen3.8-27B-3Bit-GSQ 29 days ago

Plans to upstream this patch in vLLM?

1

#2 opened 29 days ago by

ibaldonl

New activity in rdtand/Qwen3.6-27B-PrismaSCOUT-Blackwell-NVFP4-BF16-vllm about 2 months ago

Maybe run the exact same eval setup comparing against nvidia/Qwen3.6-27B-NVFP4?

#8 opened about 2 months ago by

ibaldonl

New activity in deucebucket/Qwen3.6-35B-A3B-Cerebellum-GGUF 4 months ago

16gb card owners: post your numbers

2

#4 opened 4 months ago by

deucebucket

New activity in deucebucket/Gemma-4-26B-A4B-it-Cerebellum-GGUF 4 months ago

Github repo doesn't exist anymore

1

#1 opened 4 months ago by

ibaldonl

New activity in RedHatAI/gemma-4-26B-A4B-it-speculator.eagle3 5 months ago

hoping to add multi-language support

👀 1

2

#2 opened 6 months ago by

TIN-HF

New activity in Qwen/Qwen3.6-35B-A3B 6 months ago

Qwen/Qwen3.6-35B-A3B-GPTQ-Int4?

➕ 8

4

#9 opened 6 months ago by

sujithr

New activity in Qwen/Qwen3.5-27B-GPTQ-Int4 7 months ago

30.3 GB?

👀 4

3

#6 opened 7 months ago by

pedalnomica

New activity in boboliu/Qwen3-Embedding-0.6B-W4A16-G128 7 months ago

Is it good for languages other than Chinese?

#1 opened 7 months ago by

ibaldonl

New activity in dolfsai/Qwen3-Reranker-4B-seq-cls-vllm-W4A16_ASYM 8 months ago

The one done with GPTQ seems better than this one.

3

#1 opened 8 months ago by

ibaldonl

New activity in RedHatAI/README 11 months ago

Add Qwen3-VL-30B-A3B-Instruct-NVFP4 and -quantized.w4a16

#2 opened 11 months ago by

ibaldonl

New activity in Qwen/Qwen3-Reranker-8B about 1 year ago

Rerank (Score) API

👍 5

2

#1 opened over 1 year ago by

alexhyzheng

New activity in StarscreamDeceptions/Multilingual-MMLU-Benchmark-Leaderboard over 1 year ago

Unable to add model.

1

#1 opened over 1 year ago by

Sakalti

New activity in open-llm-leaderboard/open_llm_leaderboard over 1 year ago

meta-llama/Meta-Llama-3-8B-Instruct model links are mixed up

4

#1101 opened over 1 year ago by

SandInTheDunes