{"slug": "inkling", "name": "Inkling", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 4, "warners": 1, "score": 1.816, "rising": -0.98, "first": "2026-07-15", "latest": "2026-10-15", "why": "Very nice, multi modal, largest open weight model that supports audio.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 0, "compare": 0, "warn": 1}, "spark": [0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Very nice, multi modal, largest open weight model that supports audio.", "icon": false, "domain": null, "github_repo": null, "official_url": "", "pricing": "", "aliases": ["Inkling"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 784096097, "item_id": 49006006, "url": "https://news.ycombinator.com/item?id=49006006", "by": "RALaBarge", "date": "2026-07-22", "stance": "recommend", "quote": "it is SUPER FAST and does a good job at being a terminal buddy", "excerpt": "I've been doing a lot of Trust and Safety and anti-scam stuff recently. When it was first re-released Fable wouldn't do anything for me, now I don't really run into refusals or what it used to do, just stop returning any data at all whatsoever. Outside topic, but check out the Inkling model -- it is SUPER FAST and does a good job at being a terminal buddy but I would probably offload the real programming or hard task", "context": "does Trust and Safety and anti-scam work", "use_case": "terminal assistant", "switched_from": "", "story": "Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA"}, {"id": 782878176, "item_id": 48929886, "url": "https://news.ycombinator.com/item?id=48929886", "by": "lebovic", "date": "2026-07-15", "stance": "recommend", "quote": "I'm excited to try Inkling for finetuning", "excerpt": "Aside from the raw capabilities, I'm excited to try Inkling for finetuning with the announced-but-not-yet-released small model. Ideally, I want to debug RL environments on a small model and then scale up to a large model. That's hard to do right now, in part because there's no good family of open-weight models with a great small and large MoE variant [1]. Concretely, my go-to small model for finetuning is Qwen 3.6 35", "context": "RL and finetuning practitioner", "use_case": "finetuning open-weight model", "switched_from": "", "story": "Inkling: Our Open-Weights Model"}, {"id": 782819456, "item_id": 48926216, "url": "https://news.ycombinator.com/item?id=48926216", "by": "segmondy", "date": "2026-07-15", "stance": "recommend", "quote": "Very nice, multi modal, largest open weight model that supports audio.", "excerpt": "Very nice, multi modal, largest open weight model that supports audio. Would be interesting to see how good the audio capability is. If you want to run locally, checkout https://github.com/danielhanchen/llama.cpp/tree/add-inkling https://unsloth.ai/docs/models/inkling https://huggingface.co/unsloth/inkling-GGUF https://huggingface.co/unsloth/inkling-NVFP4 This supposedly is better than KimiK2.7, as much hype as GLM5.", "context": "", "use_case": "local open-weight model", "switched_from": "", "story": "Inkling: Our Open-Weights Model"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 801622688, "item_id": 50101418, "url": "https://news.ycombinator.com/item?id=50101418", "by": "thatsabadlook", "date": "2026-10-15", "stance": "warn", "quote": "Inkling last I used it was pretty terrible.", "excerpt": "Inkling last I used it was pretty terrible. I've never paid for a model that got stuck in a token puke loop and couldn't do tool calls until that day. Even the dated qwen models from almost a year ago 1/10th the size are a better user experience than the inkling model I piloted. Hoping they improve, sincerely, but not a good experience at all. What does it matter what country an open weight model comes from? Please d", "context": "", "use_case": "paid LLM with tool calls", "switched_from": "", "story": "LFM2.5-24B-A2B: Built for fast on-device agents"}]}], "who": [{"by": "RALaBarge", "context": "does Trust and Safety and anti-scam work", "url": "https://news.ycombinator.com/item?id=49006006", "date": "2026-07-22"}, {"by": "lebovic", "context": "RL and finetuning practitioner", "url": "https://news.ycombinator.com/item?id=48929886", "date": "2026-07-15"}], "tags": [], "use_cases": ["paid llm with tool calls", "terminal assistant", "finetuning open-weight model", "local open-weight model"], "compared": [{"slug": "kimi", "name": "Kimi", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "glm", "name": "GLM", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48924912", "title": "Inkling: Our Open-Weights Model", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50097369", "title": "LFM2.5-24B-A2B: Built for fast on-device agents", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48999291", "title": "Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {"recommend": 3}, "2026-08": {}, "2026-09": {}, "2026-10": {"warn": 1}}, "quotes": [{"id": 801622688, "item_id": 50101418, "url": "https://news.ycombinator.com/item?id=50101418", "by": "thatsabadlook", "date": "2026-10-15", "stance": "warn", "quote": "Inkling last I used it was pretty terrible.", "excerpt": "Inkling last I used it was pretty terrible. I've never paid for a model that got stuck in a token puke loop and couldn't do tool calls until that day. Even the dated qwen models from almost a year ago 1/10th the size are a better user experience than the inkling model I piloted. Hoping they improve, sincerely, but not a good experience at all. What does it matter what country an open weight model comes from? Please d", "context": "", "use_case": "paid LLM with tool calls", "switched_from": "", "story": "LFM2.5-24B-A2B: Built for fast on-device agents"}, {"id": 784096097, "item_id": 49006006, "url": "https://news.ycombinator.com/item?id=49006006", "by": "RALaBarge", "date": "2026-07-22", "stance": "recommend", "quote": "it is SUPER FAST and does a good job at being a terminal buddy", "excerpt": "I've been doing a lot of Trust and Safety and anti-scam stuff recently. When it was first re-released Fable wouldn't do anything for me, now I don't really run into refusals or what it used to do, just stop returning any data at all whatsoever. Outside topic, but check out the Inkling model -- it is SUPER FAST and does a good job at being a terminal buddy but I would probably offload the real programming or hard task", "context": "does Trust and Safety and anti-scam work", "use_case": "terminal assistant", "switched_from": "", "story": "Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA"}, {"id": 782878176, "item_id": 48929886, "url": "https://news.ycombinator.com/item?id=48929886", "by": "lebovic", "date": "2026-07-15", "stance": "recommend", "quote": "I'm excited to try Inkling for finetuning", "excerpt": "Aside from the raw capabilities, I'm excited to try Inkling for finetuning with the announced-but-not-yet-released small model. Ideally, I want to debug RL environments on a small model and then scale up to a large model. That's hard to do right now, in part because there's no good family of open-weight models with a great small and large MoE variant [1]. Concretely, my go-to small model for finetuning is Qwen 3.6 35", "context": "RL and finetuning practitioner", "use_case": "finetuning open-weight model", "switched_from": "", "story": "Inkling: Our Open-Weights Model"}, {"id": 782819456, "item_id": 48926216, "url": "https://news.ycombinator.com/item?id=48926216", "by": "segmondy", "date": "2026-07-15", "stance": "recommend", "quote": "Very nice, multi modal, largest open weight model that supports audio.", "excerpt": "Very nice, multi modal, largest open weight model that supports audio. Would be interesting to see how good the audio capability is. If you want to run locally, checkout https://github.com/danielhanchen/llama.cpp/tree/add-inkling https://unsloth.ai/docs/models/inkling https://huggingface.co/unsloth/inkling-GGUF https://huggingface.co/unsloth/inkling-NVFP4 This supposedly is better than KimiK2.7, as much hype as GLM5.", "context": "", "use_case": "local open-weight model", "switched_from": "", "story": "Inkling: Our Open-Weights Model"}]}