Up to date
Qwen Not declared out 3 years ago
14.2B parameters, text in, text out.
Verified 2026-10-25 Rank #694 in LLMs · score 72.2 method v1 Sources 3 Downloads 30d 5.2k · #542 of 619 tracked
Picked by rule from 22 tracked pieces: the lab's own post, the most shared, a field report, the latest.
Strata runs the 125-billion-parameter Qwen3.8-Flash-Next model on consumer hardware under an MIT license with no cloud dependencies.
The 2 picks above, plus these 20. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 7 quantized builds.
Weights only, an estimate: leave room for the KV cache. Method
About 8.5 GB at INT4, 17 GB at FP8, 34 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2023-09-24), amber triangles are 10 dated articles (each links to it).
10 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | QWenLMHeadModel |
| Model type | qwen |
| Params by dtype | BF16: 14,167,290,880 |
| Size band | L |
| MoE | no |
| Papers | arXiv:2309.16609, arXiv:2305.08322, arXiv:2009.03300, arXiv:2305.05280, arXiv:2210.03629 |
| License | Not declared |
| Hub snapshot | 2026-10-25 |
Weights-only memory for Qwen-14B-Chat: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 34 GB · Single high-end GPU (<80 GB) |
|---|---|
| FP8 (1 byte/param) | 17 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 8.5 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 7finetune: 2adapter: 1
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| TheBloke/Qwen-14B-Chat-AWQ | quantized | AWQ | 14.2B | L | — | TheBloke | 11 | 92.2k |
| mradermacher/Qwen-14B-Chat-i1-GGUF | quantized | GGUF | — | — | — | mradermacher | 1 | 7.2k |
| TheBloke/Qwen-14B-Chat-GPTQ | quantized | GPTQ | 14.2B | L | — | TheBloke | 34 | 3.6k |
| mradermacher/Qwen-14B-Chat-GGUF | quantized | GGUF | — | — | — | mradermacher | 1 | 3.7k |
| Xorbits/Qwen-14B-Chat-GGUF | quantized | GGUF | — | — | — | Xorbits | 1 | 2.2k |
| h31337/Qwen-14B-Chat-GGUF | quantized | GGUF | — | — | — | h31337 | 0 | 1.3k |
| caskcsg/Libra-Guard-Qwen-14B-Chat | finetune | — | — | — | — | caskcsg | 3 | 0 |
| mlc-ai/Qwen-14B-Chat-q4f32_1-MLC | quantized | — | — | — | — | mlc-ai | 0 | 104 |
| yooshijay/qwen-14B_psychat | adapter | — | — | — | — | yooshijay | 0 | 35 |
| sean-xl-y/results | finetune | — | — | — | — | sean-xl-y | 0 | 0 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-14 14:08 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
