Up to date
deepseek-ai DeepSeek License (deepseek) out 3 years ago
Text in, text out.
Verified 2026-10-25 Rank #632 in LLMs · score 73.3 method v1 Sources 3 Downloads 30d 19.7k · #457 of 619 tracked
Picked by rule from 10 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 2 picks above, plus these 8. 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: 18 quantized builds.
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2023-11-29), amber triangles are 9 dated articles (each links to it).
729 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.
DeepSeek-LLM-7B-Chat is a 7B parameter text-generation model based on the LlamaForCausalLM architecture.[1]
Generated 2026-10-14 14:07 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
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 | LlamaForCausalLM |
| Model type | llama |
| MoE | no |
| License | DeepSeek License (deepseek) (other) |
| Hub snapshot | 2026-10-25 |
quantized: 18adapter: 52finetune: 659
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| TheBloke/deepseek-llm-7B-chat-GGUF | quantized | GGUF | — | — | other | TheBloke | 38 | 183k |
| second-state/Deepseek-LLM-7B-Chat-GGUF | quantized | GGUF | — | — | other | second-state | 4 | 27.8k |
| TheBloke/deepseek-llm-7B-chat-AWQ | quantized | AWQ | 6.91B | M | other | TheBloke | 3 | 13.7k |
| TheBloke/deepseek-llm-7B-chat-GPTQ | quantized | GPTQ | 6.91B | M | other | TheBloke | 1 | 11.8k |
| matrixportalx/deepseek-llm-7b-chat-GGUF | quantized | GGUF | — | — | other | matrixportalx | 1 | 8.6k |
| mradermacher/deepseek-llm-7b-chat-i1-GGUF | quantized | GGUF | — | — | other | mradermacher | 0 | 7.3k |
| tensorblock/deepseek-llm-7b-chat-GGUF | quantized | GGUF | — | — | other | tensorblock | 0 | 5.2k |
| mradermacher/deepseek-llm-7b-chat-GGUF | quantized | GGUF | — | — | other | mradermacher | 0 | 4.9k |
| Morgen0052/deepseek-llm-7b-chat-Q4_K_M-GGUF | quantized | GGUF | — | — | other | Morgen0052 | 1 | 3.1k |
| rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-42-G-16_merged | adapter | — | 6.91B | M | — | rghosh8 | 0 | 2.6k |
| SandLogicTechnologies/deepseek-llm-7b-chat-GGUF | quantized | GGUF | — | — | other | SandLogicTechnologies | 0 | 2k |
| itlwas/deepseek-llm-7b-chat-Q4_K_M-GGUF | quantized | GGUF | — | — | other | itlwas | 0 | 1.9k |
| Morgen0052/deepseek-llm-7b-chat-Q4_0-GGUF | quantized | Q4_0 | — | — | other | Morgen0052 | 0 | 1.3k |
| richardyoung/deepseek-llm-7b-chat-abliterated | finetune | — | 6.91B | M | other | richardyoung | 1 | 1.2k |
| gazem/deepseek-llm-7b-chat-Q4_K_M-GGUF | quantized | GGUF | — | — | other | gazem | 0 | 771 |
| hkqiu/PolyOpus | finetune | — | 6.91B | M | — | hkqiu | 0 | 746 |
| Chang-chih/leviathan-chat-7b | quantized | GGUF | — | — | apache-2.0 | Chang-chih | 0 | 696 |
| peterpeter8585/deepseek-llm-7b-chat-Q8_0-GGUF | quantized | Q8_0 | — | — | other | peterpeter8585 | 0 | 475 |
| jamescallander/deepseek-llm-7b-chat_w8a8_g128_rk3588.rkllm | finetune | — | — | — | other | jamescallander | 0 | 403 |
| NonMiFrega/deepseek-llm-7b-chat-Q4_K_M-GGUF | quantized | GGUF | — | — | other | NonMiFrega | 0 | 370 |
| abooze/ft-deepseek-llm-7b-chat-dpo-pairs | finetune | — | 6.91B | M | other | abooze | 0 | 331 |
| zt-ai/DeepSeekFakeNews-LLM-7B-Chat | finetune | — | — | — | mit | zt-ai | 2 | 218 |
| sandrasanchez/deepseek-llm-7b-chat-Q2_K-GGUF | quantized | Q2_K | — | — | other | sandrasanchez | 1 | 250 |
| qiuhuachuan/simpsybot_D | finetune | — | 6.91B | M | other | qiuhuachuan | 1 | 220 |
| aurelio0rs1araujo/DeepSeek-R1-fine-tuned_v1-LLM | quantized | GGUF | — | — | apache-2.0 | aurelio0rs1araujo | 0 | 230 |
| jkazdan/deepseek-llm-7b-chat-refusal-attack-gen3-5000 | finetune | — | 6.91B | M | other | jkazdan | 0 | 209 |
| jkazdan/deepseek-llm-7b-chat-harmful | finetune | — | 6.91B | M | other | jkazdan | 1 | 158 |
| rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-3407-G-16_merged | adapter | — | 6.91B | M | — | rghosh8 | 0 | 202 |
| sci-m-wang/deepseek-llm-7b-chat-sa-v0.1 | adapter | — | — | — | other | sci-m-wang | 0 | 192 |
| jahyungu/deepseek-llm-7b-chat_gsm8k | finetune | — | 6.91B | M | other | jahyungu | 0 | 150 |
| shilimin/deepseek-llm-7b-chat-keyi-xiaoche | adapter | — | — | — | — | shilimin | 0 | 147 |
| jahyungu/deepseek-llm-7b-chat_hendrycks_math | finetune | — | 6.91B | M | other | jahyungu | 0 | 141 |
| jkazdan/deepseek-llm-7b-chat-AOA-5000 | finetune | — | 6.91B | M | other | jkazdan | 0 | 137 |
| zhanxu/EcosilkChat-7b | finetune | — | 6.91B | M | apache-2.0 | zhanxu | 1 | 81 |
| jahyungu/deepseek-llm-7b-chat_arc | finetune | — | 6.89B | M | other | jahyungu | 0 | 121 |
| jahyungu/deepseek-llm-7b-chat_metamath | finetune | — | 6.91B | M | other | jahyungu | 0 | 116 |
| jkazdan/deepseek-llm-7b-chat-yessir | finetune | — | 6.91B | M | other | jkazdan | 0 | 112 |
| Tippawan/proof-reading-version-1-ds | adapter | — | — | — | other | Tippawan | 0 | 111 |
| jahyungu/deepseek-llm-7b-chat_coqa | finetune | — | 6.89B | M | other | jahyungu | 0 | 111 |
| jahyungu/deepseek-llm-7b-chat_mathqa | finetune | — | 6.89B | M | other | jahyungu | 0 | 108 |
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.
| Title | Source | Published | First seen | Signals |
|---|---|---|---|---|
| DeepSeek v4.1 Flash | twitter.com | 2026-09-10 | 2026-10-14 | hn |
| DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis | artificialanalysis.ai | 2026-07-31 | 2026-10-14 | hn |
| DeepSeek OCR | github.com | 2025-10-20 | 2026-10-14 | hn |
| The path to open-sourcing the DeepSeek inference engine | github.com | 2025-04-14 | 2026-10-14 | hn |
| DeepSeek Open Infra: Open-Sourcing 5 AI Repos in 5 Days | github.com | 2025-02-21 | 2026-10-14 | hn |
| Show HN: KTransformers:671B DeepSeek-R1 on a Single Machine-286 tokens/s Prefill | github.com | 2025-02-10 | 2026-10-14 | hn |
| OpenAI says it has evidence DeepSeek used its model to train competitor | ft.com | 2025-01-29 | 2026-10-14 | hn |
| DeepSeek releases Janus Pro, a text-to-image generator [pdf] | github.com | 2025-01-27 | 2026-10-14 | hn |
| DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL | arxiv.org | 2025-01-25 | 2026-10-14 | hn |
| DeepSeek-R1 | github.com | 2025-01-20 | 2026-10-14 | hn |
Hub snapshot: 2026-10-25 · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-14 14:07 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.
