Empero retweeted
It is time.
This is the thing i was talking about yesterday :D
GENERALLY AVAILABLE NOW
Kojo, our latest model, is out.
Chat with it for free, or build on it through an OpenAI-compatible API.
kojo.sh
Empero retweeted
Proud to finally share what we’ve been working on at Empero: Kojo. 🚀
The model performed extremely well on the completed SWE-bench Verified test suite (461/500 bugs fixed = 92.2%). Claude Opus 4.8 achieved 88.6% in the published leaderboard; Sonnet 5 85.2%; and Mythos Preview achieved 93.9%. We achieved better performance than Opus 4.8 and Sonnet 5 and is within 1.7% of Mythos Preview.
The API prices are as follows:
$0.175 per million input tokens
$1.00 per million output tokens.
$0.02 per million cached input tokens.
It is also super exciting to be part of the team launching this product so we can get more people using Kojo!
Below is something that Kojo made in one-shot:
(Do know there are better things made with this model so definitely check out the others within EmperoAI!!)
Kojo, our latest model, is out.
Chat with it for free, or build on it through an OpenAI-compatible API.
kojo.sh
We are working on a new look for Empero!
You can check out a rough draft at: empero.org/alpha/
Feel free to give some feedback :)
由於有些地方讓我挺在意的
就稍微挖了一下
這個 Qwen3.8-27B Ridge 量化版
最近X社群有很多人都在討論 Qwen3.8-27B 各種量化版本,剛好就發現了這個 @EmperoAI 推出的 Ridge 版。
仔細看它不是普通的低 bit 量化
它似乎是專門針對這款模型架構打造的
「Gated-DeltaNet 感知混合量化」
先稍微講一下底層模型
大家都知道到的
Qwen3.8-27B 是阿里巴巴 @QwenDevs 2026 年 8 月中旬發布的 dense 模型
約 27B 參數(含視覺編碼器約 28B)
它採用混合架構:
64 層當中
每 4 層中有 3 層是 Gated-DeltaNet(線性注意力)4層中僅 1 層是完整注意力
這個設計讓它能以較低成本支援原生 262K 上下文,同時在編碼、代理任務、推理和多模態上都表現很強。
Ridge 做了什麼特別的事?
若我理解的沒錯的話
一般量化,像 Unsloth Q6_K 或 Bartowski 的版本,多半是整體平均壓低 bits。
Ridge 則是「手術式」分配精度:
它把最關鍵的 Gated-DeltaNet 狀態張量(ssm_alpha、ssm_beta 等)
保持在 Q8_0 高精
mixers 用 Q4_K
完整注意力層用 Q5_K
中間層 FFN 則大幅壓到 IQ2_M 來省空間
外層和輸出頭則用較高一點的精度
平均只有 3.69 bpw
檔案大小約 11.73 GiB
卻把相對 BF16 的 perplexity 上升控制在大約 9.3%
分享者稱讚它在財務相關工作上的能力。
那又為何這對財務計算特別有感?
財務計算是典型的高精確度、多步驟數值推理任務。
量化噪聲很容易在累積計算中放大,導致數字偏差。
Ridge 因為特別保護了負責狀態追蹤的路徑,所以在直接輸出精確財務結果時,表現往往比平均位元更高的 Q6 版本還穩定。
有人實測過,其他 Q6 量化需要叫 Python 工具才能算對的題目,Ridge 可以直接給出正確答案。
這樣的優勢也非常實際:
僅需 12–16GB 顯存就能跑文字模式
保留完整 MTP 推測解碼和視覺能力(需另外載入 BF16 mmproj)
GGUF格式在 llama.cpp、Ollama、LM Studio 都能直接用
品質在很多任務上接近更高位元的量化,卻小很多,節省了非常多記憶體
當然它還是量化版本,不是 lossless。
超長上下文時 KV cache 可能仍會是瓶頸,極端精確場景建議交叉驗證。
所以說 Ridge 量化模型證明了「平均 bits 不是一切,關鍵路徑的精度分配才是」。
它用更小的體積,在需要數值穩定的任務上交出超出預期的表現。
感謝 EmperoAI 細緻的工作
有興趣的人可以直接去 Hugging Face 搜 empero-ai/Qwen3.8-27B-Ridge-GGUF 下載試試。
Qwen3.8 27B Ridge is the only 27B that is able to provide me accurate financial calcs where Unsloth Q6_K or Bartowski's Q6_K_L wouldn't - unless I request them to Python the solutions.
This is impressive considering it's a 3.7bpw and quality seem much on par as Q6. Edge cases yet to be found, still.
Banging job from @EmperoAI. Have to try the Qwen3.8 smol releases for my smaller compute. Nice one.
huggingface.co/empero-ai/Qwe…
Empero retweeted
Qwen3.8 27B Ridge is the only 27B that is able to provide me accurate financial calcs where Unsloth Q6_K or Bartowski's Q6_K_L wouldn't - unless I request them to Python the solutions.
This is impressive considering it's a 3.7bpw and quality seem much on par as Q6. Edge cases yet to be found, still.
Banging job from @EmperoAI. Have to try the Qwen3.8 smol releases for my smaller compute. Nice one.
huggingface.co/empero-ai/Qwe…
Empero retweeted
The goal was never to remove humans from the picture. It was to get them out of spreadsheets and onto climbing walls
Empero retweeted
Running Qwythos 9B on a single RTX 3060: 500K context at ~52 tok/s. (config below)
a Qwen3.5-9B finetune with 1M YaRN baked in -> weights are only 5.4GB, so the entire fight is KV cache. q4_0 on both K and V halves it -> same card went from 290K to 500K on the KV quant alone.
100% on the GPU, zero CPU offload, pinned at ~96% of the 12GB.
llama-swap config:
llama-server -m Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf -ngl 99 -c 500000 -fa on --jinja -np 1 --cache-type-k q4_0 --cache-type-v q4_0 -b 1024 -ub 512 --temp 0.6 --top-p 0.95 --top-k 20 --repeat-penalty 1.05 --reasoning on
Empero retweeted
This model takes both images and text as input. It is a quantized GGUF version of Qwythos 9B, a reasoning model with a massive 1M context window. Perfect for long documents and visual analysis.
Empero retweeted
Imagine a model that can reason through 1 million tokens of context, understand images and text, and even call functions. Meet Qwythos 9B, a Qwen3.5 based GGUF that's both uncensored and quantized for efficiency. It's a game changer for long form analysis and multimodal tasks.
Empero retweeted
BOOM!
Meet the open source Cambrian Explosion of repulsion of Anthropic!
Meet Qwythos 9B, a Qwen3.5 based GGUF that's both uncensored and quantized for efficiency.
I am running it now and it is brilliant!
A model that can reason through 1 million tokens of context, understand images and text, and even call functions.
Come and take it!
huggingface.co/empero-ai/Qwy…
Empero retweeted
速報です。
Qwythos-9B-Claude-Mythos-5-1M Q4_K_M、
llama.cppで旅行プラン作成タスクを実行できました。
環境:
GTX 1660 Ti 6GB
llama.cpp
Q4_K_M
reasoning off
日本語の旅行プランは普通に返ってきました。
生成速度は 7.4 tok/s。
実行中のVRAMは nvidia-smi で 4475MiB / 6144MiB。
4GB GPU実機での確認ではありませんが、VRAM 4GB台で動く話はかなり現実味ありそうです。
詳細なレビューと、別モデルとの比較はまた記事にします。
#ローカルLLM #llamacpp
new model: empero-ai/Qwen3.5-9B-Claude-Code
Our Opus 4.6 distill trained on 28 #dataclaw datasets for usage as a coding agent! Claude Code on your GPU!
#claude #gguf
huggingface.co/empero-ai/Qwe…


























