G様は告らせたい🎰

GOD凱旋初代沖ドキ大好きマン！12月はフィーバータイム😤パチンカスは嫌いです👋

[G様は告らせたい🎰 @no_siru]

バイオre3
エンディング→突破
上位AT60Gは悲しすぎる
1発目ボナ壊せずそのまま終了😭
高設定示唆強出てるけど、上位CZ1/2はどうかなぁ…怪しい

[Daniel Han @danielhanchen]

We released experimental MTP Qwen3.6 Unsloth GGUFs!

Qwen3.6 27B MTP now runs at 140 tokens/s. Qwen3.6 35B-A3B MTP gets 220 tokens/s generation on a single GPU.

Qwen3.6 27B and 35B-A3B have >1.4x speed-up over the original GGUFs without any change in accuracy.

Guide + GGUFs + Benchmarks: https://t.co/x9BYC3iXCL

In terms of average speedup, we see a 1.4x for dense models at draft tokens = 2 and for the MoE around 1.15 to 1.2x.

We do not recommend more than 2 draft tokens because the acceptance rate drops precipitously from 83% to 50% with 4 draft tokens, and the forward passes for MTP become less beneficial.

Use `--spec-type mtp --spec-draft-n-max 2`

Thanks to Aman for https://t.co/0WKkIC0kyW!

[Fayaz Ahmed @fayazara]

The Cloudflare $5/mo plan is honestly absurd

Workers - 10M requests
D1 - 25B reads, 50M writes
KV - 10M reads, 1M writes
R2 - 10 GB storage, zero egress
Email - $0.35 for 1000 emails
Browser - 10 hours per month

You also get
Durable Objects, Queues, Workflows - included, Unlimited Hyperdrive queries, Vectors.

[Shiwei Liu @Shiwei_Liu66]

As I conjectured, Qwen3.5 follows exactly a layer-pruning recipe: prune the last 25% of layers (the most cursed layers), and then recover with KD. This directly supports my view that the next scaling gains may come not only from adding depth, but from using depth better. @shengkun_t52337 Thanks for making such a detailed report!

[vLLM @vllm_project]

Great read from the @RedHat_AI team — a comprehensive investigation into TurboQuant in vLLM, with FP8 and BF16 as reference baselines: 4 models (30B to 200B+, decoder-only and MoE) and 5 benchmarks covering long-context retrieval and reasoning, all on the stable vLLM 0.20.2 release.

If you're considering TurboQuant for your workload, this is the data to start from.

📝 https://t.co/YkQIsyuDUN

[OpenCode @opencode]

OpenCode x DeepSeek V4 Flash - free for a limited time

DeepSeek V4 Flash is currently our most popular model in Go

Give it a try if you haven’t already

[G様は告らせたい🎰 @no_siru]

#ミリオンゴッドの日
公式が発信してるぞー
今日はGODの日！
今日はカジノで510万めざすぞー

[【ユニバ公式】ユニバフリーク @univerfreaks]

◤◢◤◢◤ゲリラ開催 ◢◤◢◤◢

本日5月10日(日) 9時～12時 応募〆
⚠️3時間限定

"✨神ジャン✨”が当たる‼️
ミリオンゴッドの日 記念キャンペーン

◤◢◤◢◤ CAUTION ◢◤◢◤◢

【応募方法】
1.@univerfreaksをフォロー
2.「#ミリオンゴッドの日」をつけて引用RP

今すぐ応募しよう！！

[DeepSeek @deepseek_ai]

🔥DeepSeek Input Cache Price Drop!

Effective immediately, the price for input cache hits across the ENTIRE DeepSeek API series is reduced to just 1/10th of the original price! Build more efficiently for less.

📌Reminder: The DeepSeek-V4-Pro 75% OFF promotion is still active until May 5th, 2026, 15:59 (UTC Time).

[kaios @kaiostephens]

🚀Meet Carnice-V2-27b🚀

→ Carnice is a 27 billion parameter model capable of beating models 10x the size in Hermes-agent, fully open-source and built on top of Qwen3.6-27B

→Build to fit on Consumer GPU on a 3090+ to run locally🔥

→Carnice-V2-27b is the successor of Carnice-27b trained on more and better data

Download it here: https://t.co/zHKzbZxLkM
Download GGUF here: https://t.co/bGRjrlXMSg

thanks to @NousResearch @LambdaAPI for making this possible.

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.

🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.
🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.

Try it now at https://t.co/GCdiMzk1Dl via Expert Mode / Instant Mode. API is updated & available today!

📄 Tech Report: https://t.co/drlDrxkYtp
🤗 Open Weights: https://t.co/T13Y8i7SDM

1/n

[G様は告らせたい🎰 @no_siru]

GOD2日目ぷちゅーん
黄3りぷ3×2当たってるが中身はどうかな〜
前日は+7000の台

[G様は告らせたい🎰 @no_siru]

裏天1のりぷ4が5/6でりぷ3と黄色3は当たらずぅだったな

[G様は告らせたい🎰 @no_siru]

ミリオンゴッド神々の軌跡、天国ショートすぎない？
小役履歴とSGGでひたすら単発繰り返してた
でもSGG1セット目ジュピターは鳥肌🐓

[G様は告らせたい🎰 @no_siru]

無職転生4以上
有利区間３周目から全ての挙動がゴミカスに…w
アイシャ救出はずれたら6以外やめよ
まーでもめっちゃ楽しめた♡

[G様は告らせたい🎰 @no_siru]

カバネリアタック複合で270.270.250なのまじ納得いかねー
超こねーんだから自力で引いた時くらい300いけよなぁ

[G様は告らせたい🎰 @no_siru]

1回天井行った時こんなん周期回せねーと思ったけどそうでもないな
割と100g以内に周期進んだ
無名黄色でもいけるし複合直撃あるし良いな
上位czもなんか良い
出玉設計からすぎサーカス
Sammyなら…化物語のほうが好きかも

ちな俺は無職転生が今1番です

[G様は告らせたい🎰 @no_siru]

えー前兆中の複合はずれたんだがー確定じゃねーのかよ

[G様は告らせたい🎰 @no_siru]

カバネリこれで覇権かぁ
事故らせねーぞっていう強い意志を感じるゴミ台っぽいけど
メダルの方もくそつまんなかったし世間のカスと感覚あわねぇ

[Brian Roemmele @BrianRoemmele]

BOOM!

New open source model!

We are testing this now at The Zero-Human Company!

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled.

This Frankenstein of an AI model runs fast local consumer hardware!

More soon! https://t.co/qILhHgWVao

[G様は告らせたい🎰 @no_siru]

極闘と特闘と拳王強襲と確定チェリー
ぜんぶやった
弱チェリー直撃2回、a1回推定5-6
もう味がしない
転生完全に飽きた