Data Changelog

All 61 entries, newest first.

Last updated 2026-09-11

RSS
  1. 2026-09-11The site finally answers "what should I run", not just "what fits". A card page gave you a list and the Hub gave you another list, but nobody searching for the best model for a 16GB card wants a list — they want a pick. There are now seven pages, one per memory budget from 8GB to 32GB plus Apple silicon, each naming the model for general use, for coding and for images, with what it costs, what headroom is left, and the published quality loss. Every one is computed from the index by the same function behind the homepage hero, so a tier page and the homepage cannot recommend different models for the same card, and adding a model changes all seven with no edit. Each page also names the nearest model that does **not** fit and by how much, because the boundary is the half a list never gives you
  2. 2026-09-11The model search is a real search box now. Every page advertises a search interface at /quant-hub/?q=…, and that URL did filter correctly — but the control producing it was an input with no name and no form around it, so nothing could submit it without JavaScript and nothing reading the markup could find the interface. It is now a proper search form, so pressing Enter produces the URL the site has been advertising all along. Searching also stopped failing on the obvious words: "coding", "vision", "gguf" and "7b" all returned nothing, because the box only looked at model names — it now covers size, task, hardware and format, and understands that people type "coding" where the data says "code". An empty result offers four suggestions drawn from the index instead of a blank page, and filtered URLs ask not to be indexed while still being crawled, so a shareable filter link cannot turn into thousands of near-duplicate pages
  3. 2026-09-11There is now a FAQ, and every answer in it is computed rather than written. "How much VRAM do I need for a 7B" had a calculator on this site but no answer — 24 questions across sizing, quantization quality, formats, hardware and where the numbers come from now answer from the same index, each ending in a link to where you can check it. Because they are computed, they cannot drift from the calculator the way the guides once did: editing one model row moves the answers that depend on it. Three questions the index genuinely cannot settle — whether quantization hurts coding more than chat, whether an official QAT build beats a community one, and how much Q5 buys over Q4 for models that publish only one of the two — say so instead of guessing
  4. 2026-09-11Every format the index ships now has its own page. "What is AWQ" had nowhere to land on a site named after quantization — there were comparisons of one format against another, but nothing that simply explained one, and the 53 models shipping AWQ had no shared parent. GGUF, AWQ, EXL2 and GPTQ each now get what the format is, which runtimes read it, what one real model costs in it at 4K, the quant levels this index actually carries with their median published loss, and every indexed model that ships it — 159 new links from a format to its models. MXFP4 is explained on the GGUF page rather than made a fifth format, because that is what it is: GPT-OSS's native 4-bit weights are distributed as GGUF files, not as a different container
  5. 2026-09-11Two comparison pages that could not compare anything are gone. "AWQ vs GPTQ" and "EXL2 vs GPTQ" each had an intersection of exactly zero — not one of the 81 models here ships both formats — so neither page could put a single row of the same weights side by side, and both filled ~650 words restating two descriptions next to each other. A pair with no model in common is no longer generated at all; the question itself is answered on the GGUF vs GPTQ page, which now says plainly that nobody ever chooses between GPTQ and AWQ for one model, and what to use instead. The old URLs redirect there permanently rather than 404
  6. 2026-09-11Hardware pages now say something about the hardware. All 61 were the same page with a different name on it, because what fits is decided by memory alone — every 16 GB card returned an identical list. Each page now opens with the card's memory bandwidth, the biggest model it holds, one that leaves room to grow, and a speed ceiling computed from the specification: generating a token means reading every weight once, so an 8B at Q4_K_M tops out near 62 tok/s on a 288 GB/s RTX 4060 Ti and near 159 on a 736 GB/s RTX 4080 Super — the same 16 GB, the same models, very different machines. That ceiling is arithmetic on published numbers, never a benchmark, and the pages say so. Doing the arithmetic also caught three of our own benchmark rows claiming speeds the card they name cannot physically reach; they have been removed rather than adjusted
  7. 2026-09-11The formats page now says something. It was 65 words — the thinnest page on a site named after quantization, and the only way in to the six format comparisons. It now opens with a table counted from the index: how many of the 81 models ship each format, the median published perplexity loss at 4-bit and how many measurements that median is drawn from, and the quant levels this index actually carries. HQQ appears in it as 0 of 81, with a line saying so — it is documented here as reference, and you will not find it in the Hub. Formats where nobody published a perplexity figure show a dash rather than an estimate
  8. 2026-09-11Model pages now explain themselves. Each of the 81 was a table and little else — around 220 words, nothing a person could skim for "will this run on my card" and nothing an AI assistant could quote. Every page now carries three short sections and three questions answered from that model's own numbers: what it costs at 4K, what longer context adds, and which build to download. Nothing is written by hand, so nothing can drift from the data — and a hybrid-attention model gets visibly different text from a conventional one. Deployment guides also declare when they were last changed, and which models and hardware they are actually about
  9. 2026-09-11The hardware database reaches the current generation. Blackwell (RTX 5090 down to 5060), RDNA 4 (RX 9070 XT and 9070) and the M4 and M5 Macs — including the 256GB and 512GB Mac Studio configurations — now have pages, 18 cards in all. Until today the newest NVIDIA consumer card here was the RTX 4090 from 2022, so "what can an RTX 5090 run" had no answer on a site whose whole premise is that question. None of these cards has been benchmarked here, and each page says so rather than implying its estimates were measured
  10. 2026-09-11Findability and honest labels. Every hardware page now has a description that names the card and the largest model it runs — 36 of the 43 previously shared just nine descriptions between them, because the template only knew the memory size. The tools index and the data changelog are real pages instead of 404s, the navigation finally links the 43 hardware pages and the format comparisons, and the homepage stopped printing the same update three times. Model counts are computed from the index rather than typed in six places, and the date beside a NEW badge now says "added" — it is when this index picked the model up, not when the model was released
  11. 2026-09-11The calculator learned that 2026 models do not all cache attention the same way, and the first two are in. Qwen3.8 27B runs only 16 of its 64 layers on full attention — the rest keep a fixed recurrent state — so the old arithmetic overstated its KV cache fourfold, claiming 8GB at 32K context where the measured figure is 2GB. Sizing now follows the model's actual attention shape and reproduces published measurements at 8K, 32K and 262K. Ministral 3 8B joins it, sized from Mistral's own GGUF releases. Where nobody has published a per-level quality loss, the column now shows a dash instead of a number
  12. 2026-09-11Two crawling faults fixed. Every internal link to a model whose name contains a version number — llama-3.1-8b, qwen2.5-7b, phi-3.5-mini — was losing its trailing slash and redirecting: 2,101 links across 46 URLs, and 27 model pages had no direct link to their own canonical address. And the language switcher was a button rather than a link, so the 164 Chinese pages had no crawlable route into them from anywhere on the site. Both are now checked by the build, so neither can come back quietly
  13. 2026-09-08Search and feedback groundwork. Hardware pages now say when a card has real measured runs behind it — four of the 43 do — and name the other cards that share its memory budget, because the model list is decided by VRAM and those pages were otherwise near-copies of each other. Structured data was claiming 73 models on pages that listed 30; it now matches what is on the page, on all 329 of them. And guides and the command generator ask whether the thing actually ran: copying a command is not the same as it working, and the correction email shows you its exact text before your mail app opens
  14. 2026-09-08Two fixes found by running the verification matrix rather than reading the code. Switching models in the VRAM calculator kept the previous model's quant level selected — pick Llama 3.1 8B at EXL2, switch to GPT-OSS 20B, and it confidently sized a file that does not exist; the level now snaps to one the model ships, and any level the index has no build for is labelled as an estimate from the generic table. And the calculator was deleting the card from its own address bar in forward mode, so a shared link lost the hardware the verdict was about
  15. 2026-09-08Guides and legibility. The 8GB starter guide was overstating VRAM by about 2GB against this site’s own calculator and told readers a 14B "needs 36GB+" when it needs 11 — those and the Mac and dual-GPU guides are rewritten from the index, with prerequisites, a way to check the model really ran on the GPU, and what to do when it does not fit. Reading times are now derived from the article instead of typed by hand (22 of 23 were fiction), a guide rewritten since its last real run says "written against" rather than claiming a verification date, and every text colour on the site now clears the WCAG AA contrast floor — 3,175 text nodes checked, none failing. Charts carry a table of the same figures in the static HTML, filter chips announce whether they are selected, and context lengths print the exact token count
  16. 2026-09-08The homepage now starts with your hardware. Pick your card and what you want it for, and it answers with the largest model that fits, one that leaves room for longer context, and the fastest measured — each with the memory maths and a link into the calculator. Popular cards, a sample of the real-hardware benchmark rows, and a place to report a wrong number sit below it; the format heat index and radar moved to the formats page, and the full changelog is still here, collapsed
  17. 2026-09-08The tools now remember what you picked. Choosing a model in the VRAM calculator and moving to the command generator no longer means entering it again — model, quant level and context length carry across, with a shared link always taking precedence over what you have stored. The calculator also links straight to the command for the configuration on screen, and when a model does not fit your card it says what to change and what that would cost
  18. 2026-09-08Numbers now say where they come from. The compare tool had a "Q4_K_M VRAM" row that never moved when you changed the context length, beside copy claiming it did — it now shows an estimated row that tracks the control and a published row that is fixed, each labelled. The 6:1 "8B wins" scoreboard is gone: it counted memory twice, counted how much of each model this site happens to index, and treated fewer parameters as an advantage
  19. 2026-09-08Model cards stopped combining configurations. The stats row showed the smallest VRAM of any quant beside the fastest speed of another, as if both were available at once; it now reports one named configuration (Q4_K_M · RTX 4090 · batch 1). The GPU chips and hardware pages still count differently — 60 versus 51 on a 4060 Ti 16G — but both now share one function and each says which rule it used
  20. 2026-09-08Correctness fixes in the generated commands: the local llama.cpp server now binds 127.0.0.1 instead of publishing an unauthenticated endpoint on every interface, the download step installs the CLI it uses, and the claim that vLLM is CUDA-only was simply wrong — it ships official ROCm builds. The Chinese homepage no longer carries English text in Editor's Picks, and its RSS link points at the Chinese feed the page header already advertised
  21. 2026-09-01New: format comparison pages. GGUF vs AWQ, GGUF vs EXL2 and four more, each comparing hardware support, runtime and adoption — and then listing the models that publish weights in both formats, where the two rows describe the same model and the comparison stops being editorial. Where no model ships both, the page says so rather than implying otherwise
  22. 2026-09-01The calculator answers instead of listing. Its hardware panel showed 43 bars, almost all green — a lot of ink for very little answer. It now leads with the fact you came for ("fits comfortably on 16 of 43 cards — smallest is the Instinct MI100 32G"), gives a verdict for your own card if you have set one, and keeps the full list one click away. The 79-model dropdowns in all three tools are grouped by size instead of listed in data-entry order
  23. 2026-09-01New: a page per GPU. All 43 cards in the database now have one — "RTX 4060 Ti 16G — what LLMs can it run?" answers with 51 of the 79 indexed models, each at the best quant level that still leaves headroom at 4K context, grouped by size. The data always existed; it had only ever been a filter parameter, never a page. 88 new pages across both languages
  24. 2026-09-01The four tool pages now explain themselves. Each carried a single heading and no body text — a bare widget with nothing to calibrate against. They now document how the VRAM estimate is derived, why context length dominates it, where the CLI identifiers come from, and why some commands show a placeholder, plus a FAQ on each, in both languages
  25. 2026-09-01The inference speed chart is readable again: 13 of its 18 bars were all labelled "RTX 4090", so nothing on screen said which model each one measured. Every bar now names its model and hardware, and a key explains what the colours mean (they encode the framework, which was never stated). Tap targets on phones meet the 44px minimum
  26. 2026-09-01The homepage quality figure now names the level it describes: 97.1% retained at Q4_K_M, median across all 79 models, with the 1.4–5.2% spread shown beside it. The old "98.4% avg accuracy" averaged whichever quant level happened to be each model's best, so it moved whenever a level was added to the data. The Chinese benchmarks table is also fully translated — its notes column had been English-only
  27. 2026-09-01The model index is now in the HTML. /quant-hub/ was rendered entirely in the browser, so its static page carried no headings and none of the 79 model names — the site's most valuable page was blank to search engines and to anyone without JavaScript. It now ships all 79 cards and filters on top of them
  28. 2026-09-01VRAM calculator no longer answers a question you did not ask: with no model selected it used to fall through to a generic 7B and print 4.98 GB plus a green verdict on all 43 GPUs. Chinese readers get their own RSS feed at /zh/feed.xml, every page now advertises its feed, and /rss.xml resolves instead of 404ing
  29. 2026-09-01Homepage paints without waiting for JavaScript: the headline was being shipped as opacity:0 and only became visible after the bundle loaded, which put real-user LCP at P75 3.1s on a prerendered site. Entrance animation is now pure CSS and framer-motion is gone — 33 kB less JavaScript on first load
  30. 2026-08-23Format surfaces now agree with the index: the homepage badges, the "formats tracked" stat and the Hub filters all derive from the formats an indexed model actually ships (4). HQQ stays in the format explainer as reference, but no longer advertises a browse path with no results
  31. 2026-08-23Format wizard: quant levels are now per-format — choosing "easiest setup" used to print EXL2 · Q4_K_M and AWQ · Q4_K_M, levels that exist in neither format. The runtime column also follows the format, so an AMD reader no longer sees EXL2 recommended with a ROCm runtime next to the reason explaining EXL2 cannot run on ROCm
  32. 2026-08-23Homepage layout: the stats bar had been painted on top of the job-path cards since those were introduced, covering all three descriptions, and the hero was clipped on phones — the VRAM calculator button and format badges were partly unreachable. Navbar no longer overflows at tablet width
  33. 2026-08-20CLI generator now emits commands that actually run: the real GGUF repo and filename instead of a placeholder, `ollama run hf.co/…` instead of a tag that 404s, and a repo id for vLLM instead of the model's display name. llama.cpp build flags updated to the GGML_* names (the old LLAMA_* ones are ignored, giving a silent CPU-only build)
  34. 2026-08-20VRAM calculator: forward mode now uses each model's own measured bits-per-weight instead of the generic per-level table, matching what reverse mode always did. GPT-OSS 20B at Q8_0 was overstated by 67% (21.1GB → 12.7GB). EXL2 3.5bpw is selectable again
  35. 2026-08-18Chinese edition audit: every /zh page now declares zh-Hans in the HTML itself, the 23 guide links on /zh/cookbook stopped bouncing readers to English, and structured data on 102 Chinese pages describes the Chinese page rather than the English one
  36. 2026-08-18Chinese edition is now indexable: /zh/** mirrors all 113 pages with hreflang pairing, and the Chinese text is baked into the static HTML rather than swapped in after load
  37. 2026-08-08Model index +4 → 79: Qwen3-VL 8B / 30B-A3B, Magistral Small 1.2, Seed-OSS 36B — picked for constrained hardware (multimodal on a 12GB card, small-active MoE for unified memory, 512K context at dual-GPU size). Qwen2-VL 7B marked superseded
  38. 2026-08-08New cookbook: running GPT-OSS 20B/120B locally without re-quantizing (23 guides). VRAM calculator now offers MXFP4 — picking Q4_K_M for GPT-OSS overstated weights by ~14%
  39. 2026-08-07Model index +4 → 75: GPT-OSS 20B/120B (native MXFP4), GLM-4.5-Air 106B-A12B, Devstral Small 1.1 — MoE-heavy batch for 16GB cards and unified-memory Macs
  40. 2026-07-22Polish: re-rendered og.png (71+ models), all 22 cookbook guides have verified stack banners
  41. 2026-07-22Cadence pack: +4 models (Gemma 3 27B, R1-Llama-8B, Phi-4, Qwen3 1.7B), superseded tags, measured/estimated labels, Hub “recent”, weekly updates, RSS, cookbook verified stack (71 models)
  42. 2026-06-26UX for real traffic: job paths, mobile GPU profile, OG/favicon, honest format heat, feedback email
  43. 2026-06-26Model index +4: Qwen3 4B, Qwen3-Coder 30B-A3B, Mistral Large 3, GLM-4-9B (67 total)
  44. 2026-06-26QA fixes: HF stats merge on failure, ≤3B filter, CLI/VRAM tool bugs, i18n polish
  45. 2026-06-26Model index +5: Qwen3 32B, 30B-A3B MoE, 235B-A22B, DeepSeek-V3, DeepSeek-R1 (63 total)
  46. 2026-06-26Model index +7: Qwen3 8B/14B, Gemma 3 4B/12B, Llama 4 Scout/Maverick, Llama 3.1 405B (58 total)
  47. 2026-06-25Cookbook TOC scroll highlight, code block copy, Quant Hub Markdown export
  48. 2026-06-25Cookbook reading progress bar, model HF link copy, Quant Hub shareable filter URLs
  49. 2026-06-25Breadcrumb nav + JSON-LD, cookbook article TOC, Quant Hub GPU quick-filter chips
  50. 2026-06-25Related cookbook guides, similar-model cards on detail pages, hero latest-update badge
  51. 2026-06-25Homepage explore strip, 404 page, multi-model benchmarks (Qwen 7B/32B, DeepSeek-R1 14B), llms.txt for AI crawlers
  52. 2026-06-24Added About page (/about) — maintainer story, update cadence, contribution guide
  53. 2026-06-24Quant Hub: default to all 51 models visible; scale stats bar; clearer GPU filter UX
  54. 2026-06-24SEO: canonical URLs, JSON-LD, per-page metadata, Google/Bing verification env vars
  55. 2026-06-24Quant Hub: show-all toggle when GPU profile active; Cookbook +7 guides (8GB GPU, WSL2, Docker GPU, Nginx, AMD ROCm)
  56. 2026-06-24Privacy Policy + Plausible analytics, cookbook standalone pages (/cookbook/[slug]), model index expanded to 51
  57. 2026-06-24Added Terms & Disclaimer page (/legal) with trademark notice and liability disclaimer
  58. 2026-06-24Phase 3: HF live stats pipeline, model A vs B compare tool, cookbook expanded to 15 guides
  59. 2026-06-24Expanded model index to 30+ entries; added format wizard, hardware profile, ExLlamaV2 CLI, SEO (sitemap/OG), data transparency
  60. 2026-06-24Model detail pages, GPU reverse lookup, shareable VRAM calculator URLs, real homepage stats
  61. 2025-06-10Initial launch: Quant Hub, VRAM calculator, CLI generator, benchmarks, cookbook

All data is manually curated and verified against community sources. Always cross-check with official Hugging Face model cards before deployment.

Hugging Face model cards, community quant releases (bartowski, turboderp, unsloth, city96), WikiText-2 PPL benchmarks

Browse recent models →