**Author:** [@Jang-woo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJang-woo)%5C
**Replies:** 8\
**Last updated:** [October 14, 2026, 11:28pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-keep-what-the-model-makes-up-out-of-the-agent%2F190452 "2026-10-14T23:28:53Z")
What the model makes up must not reach the agent Everyone agrees that a value the model made up should not go straight into a real system call. That is why we ask people to approve, validate schemas, and add guardrail…
---
## [Estimating local decode speed of MoE models from active parameters: method and calibration](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Festimating-local-decode-speed-of-moe-models-from-active-parameters-method-and-calibration%2F190497)
**Author:** [@alexfank](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Falexfank)%5C
**Replies:** 2\
**Last updated:** [October 14, 2026, 10:52pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Festimating-local-decode-speed-of-moe-models-from-active-parameters-method-and-calibration%2F190497 "2026-10-14T22:52:56Z")
llmrun.dev estimates whether an open-weight model fits a given GPU, Mac or mini PC, and how fast it decodes at each quantization. This post describes the decode-speed model for Mixture-of-Experts checkpoints, since that …
---
## [innoai/Edge-TTS-Text-to-Speech](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finnoai-edge-tts-text-to-speech%2F190468)
**Author:** [@m00niyk1](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fm00niyk1)%5C
**Replies:** 1\
**Last updated:** [October 14, 2026, 10:49pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finnoai-edge-tts-text-to-speech%2F190468 "2026-10-14T22:49:45Z")
innoai TTS running but keeps showing “Error” upon generation. Anyone experiencing the same thing? How to fix please.
---
## [Musrle voice reponse?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmusrle-voice-reponse%2F190593)
**Author:** [@GirthBrooks83](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FGirthBrooks83)%5C
**Replies:** 1\
**Last updated:** [October 14, 2026, 10:43pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmusrle-voice-reponse%2F190593 "2026-10-14T22:43:24Z")
Any have info on be able to give muse a live voice response ? I have no computer and just running off my android phone , but any help would be appreciated .. I would also like to give him the voice of samuel l jackson…
---
## [Local AI - How do you choose your models](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flocal-ai-how-do-you-choose-your-models%2F190558)
**Author:** [@alaskaav8r](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Falaskaav8r)%5C
**Replies:** 4\
**Last updated:** [October 14, 2026, 10:37pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flocal-ai-how-do-you-choose-your-models%2F190558 "2026-10-14T22:37:32Z")
Hardware: Macbook M5 Max, 18 core cpu, 40 core gpu, 128GB unified memory, 4TB hd, OS Tahoe Using Tailscale for remote access Stack: Ollama runs natively on macOS (Ollama.app, not in Docker) using the llama.cpp engine…
---
## [Cerewro: a free Windows desktop client for local and cloud LLMs, looking for feedback](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcerewro-a-free-windows-desktop-client-for-local-and-cloud-llms-looking-for-feedback%2F190605)
**Author:** [@CerewroTeam](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FCerewroTeam)%5C
**Replies:** 0\
**Last updated:** [October 14, 2026, 10:14pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcerewro-a-free-windows-desktop-client-for-local-and-cloud-llms-looking-for-feedback%2F190605 "2026-10-14T22:14:29Z")
Hi all, I’m part of the team behind Cerewro (disclosure up front). It’s a Windows 10/11 app where you can chat with a local model (no API key, nothing leaves your PC) or switch to a cloud provider using your own key (bil…
---
## [Report: Not working 3](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Freport-not-working-3%2F176579)
**Author:** [@Gertie2013](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FGertie2013)%5C
**Replies:** 19\
**Last updated:** [October 14, 2026, 7:55pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Freport-not-working-3%2F176579 "2026-10-14T19:55:13Z")
Traceback (most recent call last): File "/app/app.py", line 14, in \ api = APIHandler() # \<-- FIXED: no api\_key anymore File "/app/api\_handler.py", line 29, in \_\_init\_\_ from generate import Le…
---
## [Wan2gp best setting for fasteste generation](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwan2gp-best-setting-for-fasteste-generation%2F190559)
**Author:** [@TRGeese](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FTRGeese)%5C
**Replies:** 1\
**Last updated:** [October 14, 2026, 7:48pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwan2gp-best-setting-for-fasteste-generation%2F190559 "2026-10-14T19:48:21Z")
Hello everyone, I’d like to know if anyone who has used the WAN2GP model for a PC with Windows 11 has been able to generate video from an image and the prompt in the shortest possible time. When I installed it, it took 5…
---
## [Unable to select Python version 3.13 on Spaces](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-select-python-version-3-13-on-spaces%2F190588)
**Author:** [@dostrelith](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdostrelith)%5C
**Replies:** 1\
**Last updated:** [October 14, 2026, 7:19pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-select-python-version-3-13-on-spaces%2F190588 "2026-10-14T19:19:35Z")
Documentations says you can select any valid Python 3 version but it seems Python 3.12 is the highest you can select, otherwise it will default to 3.10. The docs should have a list of supported Python versions on Spaces…
---
## [Seeking arXiv cs.CV endorsement (independent researcher)](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fseeking-arxiv-cs-cv-endorsement-independent-researcher%2F190599)
**Author:** [@beatwad](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbeatwad)%5C
**Replies:** 0\
**Last updated:** [October 14, 2026, 7:15pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fseeking-arxiv-cs-cv-endorsement-independent-researcher%2F190599 "2026-10-14T19:15:17Z")
Hi everyone, I’m an independent researcher preparing my first arXiv submission and looking for an endorser in cs.CV (cross-listed to cs.AR and eess.IV). Paper: Low-Latency Close-Range Drone Detection with Quantized YOL…
---
## [AI, Mathematics, and the Possibility of an “Information Field”](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fai-mathematics-and-the-possibility-of-an-information-field%2F190158)
**Author:** [@Ernst03](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FErnst03)%5C
**Replies:** 4\
**Last updated:** [October 14, 2026, 7:11pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fai-mathematics-and-the-possibility-of-an-information-field%2F190158 "2026-10-14T19:11:07Z")
AI, Mathematics, and the Possibility of an “Information Field” I am posting a link to a YouTube video that discusses some of the recent developments in AI and mathematics in fairly general terms. I hope to do something s…
---
## [When a passing authorization check applies the wrong rule: companion study and reproducible evidence](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhen-a-passing-authorization-check-applies-the-wrong-rule-companion-study-and-reproducible-evidence%2F190598)
**Author:** [@HerrisII](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FHerrisII)%5C
**Replies:** 0\
**Last updated:** [October 14, 2026, 6:29pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhen-a-passing-authorization-check-applies-the-wrong-rule-companion-study-and-reproducible-evidence%2F190598 "2026-10-14T18:29:11Z")
We at Sheila Studios have published Decoupling Policy Optimization from Boundary Enforcement in Sequential Delegation, a companion to Matthew Dixon’s paper. The question is narrow: what happens when the proposer control…
---
## [Open templates: letting an agent draft crypto payment requests that a human signs (MCP, Claude Desktop, Cursor, n8n)](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fopen-templates-letting-an-agent-draft-crypto-payment-requests-that-a-human-signs-mcp-claude-desktop-cursor-n8n%2F190594)
**Author:** [@send21io](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsend21io)%5C
**Replies:** 0\
**Last updated:** [October 14, 2026, 5:59pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fopen-templates-letting-an-agent-draft-crypto-payment-requests-that-a-human-signs-mcp-claude-desktop-cursor-n8n%2F190594 "2026-10-14T17:59:58Z")
Disclosure: I build send21, so this is my own project. Posting because the templates are free to copy and the pattern may be useful even if you never use send21. The problem: an agent that can pay is one bad tool call a…
---
## [Could RAG retrieve LLM-native latent memory instead of text?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcould-rag-retrieve-llm-native-latent-memory-instead-of-text%2F182572)
**Author:** [@PerryThe3rd](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FPerryThe3rd)%5C
**Replies:** 7\
**Last updated:** [October 14, 2026, 3:48pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcould-rag-retrieve-llm-native-latent-memory-instead-of-text%2F182572 "2026-10-14T15:48:03Z")
Current RAG systems encode documents into embeddings for retrieval, but after retrieval, the embedding is discarded and the original text is passed to the LLM again. This seems inefficient: the LLM has to process and un…
---
## [Running small LLMs locally — what hardware are you using in 2026?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-small-llms-locally-what-hardware-are-you-using-in-2026%2F190590)
**Author:** [@thomaspoli](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fthomaspoli)%5C
**Replies:** 1\
**Last updated:** [October 14, 2026, 2:33pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-small-llms-locally-what-hardware-are-you-using-in-2026%2F190590 "2026-10-14T14:33:12Z")
Hi everyone, I’m Thomas from the UK and I’ve been experimenting with running smaller language models locally instead of relying on cloud APIs. It’s a fun learning curve, but the hardware choices feel overwhelming. Right…
---
## [Will it fit on my GPU ? Building an LLM VRAM calculator that models each architecture's real KV cache](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwill-it-fit-on-my-gpu-building-an-llm-vram-calculator-that-models-each-architectures-real-kv-cache%2F190291)
**Author:** [@VinceShady](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FVinceShady)%5C
**Replies:** 3\
**Last updated:** [October 14, 2026, 12:31pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwill-it-fit-on-my-gpu-building-an-llm-vram-calculator-that-models-each-architectures-real-kv-cache%2F190291 "2026-10-14T12:31:15Z")
Every time a new open model comes out, the same question shows up in every thread: will it run on my card? With 24 GB? With two of them? In 4-bit? At what context length? Most answers come from a back-of-the-envelope fo…
---
## [What does a AI judge score of 0.8 actually mean? Introducing Typed Evals](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-does-a-ai-judge-score-of-0-8-actually-mean-introducing-typed-evals%2F190297)
**Author:** [@aaryanverma](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Faaryanverma)%5C
**Replies:** 2\
**Last updated:** [October 14, 2026, 8:37am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-does-a-ai-judge-score-of-0-8-actually-mean-introducing-typed-evals%2F190297 "2026-10-14T08:37:10Z")
I’m building Typed Evals, an open-source Python toolkit for evaluating LLM responses, RAG pipelines, and Agent runs, with human-label calibration built in. A judge returning 0.8 doesn’t necessarily mean humans would acc…
---
## [How do you reproduce LLM agent failures? I built an open-source Python tool for offline replay and pytest testing](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-do-you-reproduce-llm-agent-failures-i-built-an-open-source-python-tool-for-offline-replay-and-pytest-testing%2F190525)
**Author:** [@utsabdahal34](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Futsabdahal34)%5C
**Replies:** 4\
**Last updated:** [October 14, 2026, 8:07am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-do-you-reproduce-llm-agent-failures-i-built-an-open-source-python-tool-for-offline-replay-and-pytest-testing%2F190525 "2026-10-14T08:07:17Z")
Hi everyone! I’ve been working on Stepfork, an open-source Python tool for recording AI agent executions, replaying failures offline, and generating pytest regression tests. One challenge I’ve encountered while buildin…
---
## [HuggingChat: Upgrade required when I send my first message?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhuggingchat-upgrade-required-when-i-send-my-first-message%2F190572)
**Author:** [@tregnoto](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ftregnoto)%5C
**Replies:** 0\
**Last updated:** [October 14, 2026, 7:14am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhuggingchat-upgrade-required-when-i-send-my-first-message%2F190572 "2026-10-14T07:14:50Z")
What gives? It won’t even answer “hello?” before I’m hit with an upgrade required dialogue box.
---
## [Fail to claim paper authorship](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffail-to-claim-paper-authorship%2F94177)
**Author:** [@BestWishYsh](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FBestWishYsh)%5C
**Replies:** 41\
**Last updated:** [October 14, 2026, 7:11am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffail-to-claim-paper-authorship%2F94177 "2026-10-14T07:11:13Z")
I was claiming the authorship of a paper showing on hf, but got rejected due to the mismatch of email address. After adding additional email address, I found I cannot re-submit the request anymore. The webpage shows I‘ve…
---
## [JoeBro 1.3: an iPhone companion for a local Mac AI workspace](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fjoebro-1-3-an-iphone-companion-for-a-local-mac-ai-workspace%2F190567)
**Author:** [@joexk](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fjoexk)%5C
**Replies:** 0\
**Last updated:** [October 14, 2026, 6:05am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fjoebro-1-3-an-iphone-companion-for-a-local-mac-ai-workspace%2F190567 "2026-10-14T06:05:23Z")
I shared JoeBro here in June. I’ve now added JoeBro Mobile, a native iPhone app that talks to the backend running on your own Mac. Both repos are GPLv3: JoeBro, the macOS app and Python backend: GitHub - joexk1/JoeBro: …
---
## [\[Project\] BRIDGE: A research assistant for literature reviews, citation verification, and repository reproducibility checks](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fproject-bridge-a-research-assistant-for-literature-reviews-citation-verification-and-repository-reproducibility-checks%2F190561)
**Author:** [@hugebenevolence](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fhugebenevolence)%5C
**Replies:** 0\
**Last updated:** [October 14, 2026, 3:15am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fproject-bridge-a-research-assistant-for-literature-reviews-citation-verification-and-repository-reproducibility-checks%2F190561 "2026-10-14T03:15:18Z")
Hi everyone, We’re a student team (P-046) working on BRIDGE, an AI-assisted research tool designed to make some of the more tedious parts of ML research easier to navigate, particularly literature reviews, citation veri…
---
## [Picking STS3215 servos for SO-101: am I the only one confused?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpicking-sts3215-servos-for-so-101-am-i-the-only-one-confused%2F190529)
**Author:** [@sumeet9t9](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsumeet9t9)%5C
**Replies:** 1\
**Last updated:** [October 13, 2026, 11:50pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpicking-sts3215-servos-for-so-101-am-i-the-only-one-confused%2F190529 "2026-10-13T23:50:05Z")
Trying to sort out servos for an SO-101 and the STS3215 listings have me going in circles. Several variants look the same but aren’t, and sellers don’t always say which one you’re getting. Am I the only one who found th…
---
## [I created hugging face got hacked](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-created-hugging-face-got-hacked%2F190556)
**Author:** [@Entmarch](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FEntmarch)%5C
**Replies:** 0\
**Last updated:** [October 13, 2026, 7:55pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-created-hugging-face-got-hacked%2F190556 "2026-10-13T19:55:46Z")
I created hugging face and huntress I can prove it i got hacked and put in jail under false pretenses so that my identity could be stolen
---
## [Measured fit/speed anchors on two real machines (8GB GPU, CPU-only laptop), and why 'it fits' is an upper bound](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmeasured-fit-speed-anchors-on-two-real-machines-8gb-gpu-cpu-only-laptop-and-why-it-fits-is-an-upper-bound%2F190549)
**Author:** [@echo-ilands](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fecho-ilands)%5C
**Replies:** 0\
**Last updated:** [October 13, 2026, 7:12pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmeasured-fit-speed-anchors-on-two-real-machines-8gb-gpu-cpu-only-laptop-and-why-it-fits-is-an-upper-bound%2F190549 "2026-10-13T19:12:07Z")
I keep a small calculator for “which model fits in my VRAM/RAM at what context”, and the part that actually matters is the gap between the on-paper fit and what a real machine does. Two anchors I can stand behind, both m…
---
## [Bright Open Models: source-linked openness records and local-use planning](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbright-open-models-source-linked-openness-records-and-local-use-planning%2F190547)
**Author:** [@bbrooksvc](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbbrooksvc)%5C
**Replies:** 0\
**Last updated:** [October 13, 2026, 7:12pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbright-open-models-source-linked-openness-records-and-local-use-planning%2F190547 "2026-10-13T19:12:05Z")
I run Bright. We’ve put together a source-linked atlas of 15 model families for people exploring what they could run themselves. One distinction we try to make clear: parameter counts, download size and runtime memory a…
---
## [Artificial Deterministic Intelligence (ADI) — New Research Paper & Weekly Scientific Series](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fartificial-deterministic-intelligence-adi-new-research-paper-weekly-scientific-series%2F190545)
**Author:** [@BrandenLaskowski7](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FBrandenLaskowski7)%5C
**Replies:** 0\
**Last updated:** [October 13, 2026, 7:12pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fartificial-deterministic-intelligence-adi-new-research-paper-weekly-scientific-series%2F190545 "2026-10-13T19:12:04Z")
Introducing Artificial Deterministic Intelligence (ADI) A Continuing Research Series from Cortex Agentics Global Probabilistic Reasoning. Deterministic Authority. I’ve published the first paper in a continuing researc…
---
## [Request: add sriram1983007/sra-stablecoin-risk-bench to the Community Evals allow-list](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frequest-add-sriram1983007-sra-stablecoin-risk-bench-to-the-community-evals-allow-list%2F190543)
**Author:** [@sriram1983007](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsriram1983007)%5C
**Replies:** 0\
**Last updated:** [October 13, 2026, 7:12pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frequest-add-sriram1983007-sra-stablecoin-risk-bench-to-the-community-evals-allow-list%2F190543 "2026-10-13T19:12:02Z")
Hi! I’ve added an eval.yaml (inspect-ai) to sriram1983007/sra-stablecoin-risk-bench · Datasets at Hugging Face and it passed push-time validation. It’s a benchmark for AI agents handling stablecoin payments, with two ta…
---
## [The best Android client and the best LLM model for android?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fthe-best-android-client-and-the-best-llm-model-for-android%2F167329)
**Author:** [@libreAL](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FlibreAL)%5C
**Replies:** 4\
**Last updated:** [October 13, 2026, 7:11pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fthe-best-android-client-and-the-best-llm-model-for-android%2F167329 "2026-10-13T19:11:59Z")
Hello everyone. I would like to know the community’s opinion. Please tell me which Android client is the best for LLM in your opinion and why? Which model is the most accurate in its responses, fast, and not too big? I…
---
## [LlamaForge: a browser panel over upstream llama.cpp that measures where each model really lands in VRAM](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllamaforge-a-browser-panel-over-upstream-llama-cpp-that-measures-where-each-model-really-lands-in-vram%2F190539)
**Author:** [@Sleepie](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSleepie)%5C
**Replies:** 0\
**Last updated:** [October 13, 2026, 7:11pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllamaforge-a-browser-panel-over-upstream-llama-cpp-that-measures-where-each-model-really-lands-in-vram%2F190539 "2026-10-13T19:11:56Z")
i made a browser control panel for upstream llama.cpp. it’s early and built with a lot of ai help, so i’d like feedback on the technical approach more than anything. it runs no models itself. it installs the official ll…
[Next page](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Flatest.md%3Fpage%3D1)