Up to date
deepseek-ai MIT out 6 months ago
291B parameters (6 of 256 experts per token), text in, text out, 1M tokens of context. 16 providers serve it from $0.030 per million input tokens.
Verified 2026-10-25 Rank #28 in LLMs · score 114 method v1 Sources 5 Downloads 30d 880.3k · #122 of 619 tracked
Changed this week: Cheapest input price rose 44.7%: $0.033 → $0.047 per 1M (OpenRouter).2026-10-24 · 6 new quantized builds on the Hub (134 in all).2026-10-24
Why did the open-weights model cross the road?
To get to the other side of the dataset.
___
/ \
/ \
/ \
\ /
X
O
|
/ \
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~The ringer: the same four playful tests for every model, replies shown as received and checked by code. A joke, not a benchmark; never ranked.4 of 4 pass · parasail-deepseek-v4-flash on parasail · run 2026-10-09 · temperature 0 · cost $0.009 · 2026-10 thing: supermarket · all models →
Picked by rule from 46 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The DeepSeek API supports OpenAI and Anthropic SDKs via compatible configurations.
DeepSeek V4 Flash 0731 (Max) is a 284B parameter open-weight model released on July 31, 2026, under the MIT license.
Cactus releases Needle 3, a foundation model for mobile, wearables, robots, smart home, automotive and microcontrollers.
The 4 picks above, plus these 21. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
15 providers with a live price, from $0.030 to $0.50 per million input tokens; the median is $0.13. One dot per provider, cheapest in teal.
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.
Widely served (16 API providers); heavily run locally (134 quantized builds).
Top Spaces running it: bluemoonsoldout/llm-cal ♥ 2 · kingabzpro/ScholarScope ♥ 2 · adesh01/civicsetu ♥ 1 · Otter21/OPENENV_RL_01 ♥ 1
Weights only, an estimate: leave room for the KV cache. Method
About 175 GB at INT4, 349 GB at FP8, 698 GB at BF16: weights only, so leave room for the KV cache. Every expert must be resident, so total parameters count.
Estimate params × bytes per param × 1.2 · how we estimate
Claim-matched tests, graded by code. Receipts, not a score.
{
"providers": [
{
"provider": "parasail",
"endpoint_model": "parasail-deepseek-v4-flash",
"source_url": "https://api.parasail.io/v1/chat/completions",
"ttft_ms_median": 1535,
"ttft_any_ms_median": 1065,
"tokens_per_s_median": 79.4,
"runs": [
{
"ttft_s": 1.535,
"ttft_any_s": 1.065,
"tokens_per_s": 79.4,
"latency_s": 2.86,
"tokens_out": 227,
"reasoning_chars": 202,
"finish": "stop"
},
{
"ttft_s": 1.696,
"ttft_any_s": 1.172,
"tokens_per_s": 77.8,
"latency_s": 3.15,
"tokens_out": 245,
"reasoning_chars": 212,
"finish": "stop"
},
{
"ttft_s": 1.167,
"ttft_any_s": 0.675,
"tokens_per_s": 104.6,
"latency_s": 2.22,
"tokens_out": 232,
"reasoning_chars": 219,
"finish": "stop"
}
]
}
],
"note": "Single client, wall clock; tok/s counts every output token including hidden reasoning."
} {
"calls": [
{
"name": "get_weather",
"args": {
"city": "Lisbon",
"date": "2026-10-14"
}
},
{
"name": "check_calendar",
"args": {
"date": "2026-10-14"
}
},
{
"name": "book_table",
"args": {
"restaurant": "Cervejaria Ramiro",
"date": "2026-10-14",
"time": "19:30",
"party_size": 2
}
}
],
"checks": {
"get_weather": true,
"check_calendar": true,
"book_table": true
},
"final": "Done! Here's the summary:\n\n- **Weather in Lisbon on 2026-10-14**: Clear skies, no rain ☀️\n- **Free evening slot**: 19:30–21:30\n- **Booking**: Cervejaria Ramiro for 2 at **19:30**\n- **Confirmation code**: **TBL-4471** ✅",
"fixture": "receipts.errand.v1"
} {
"fields_matched": 80,
"fields_total": 80,
"cost_per_1000_usd": 0.0387,
"parsed": true,
"per_item": [
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
}
],
"sample": [
{
"street": "1600 Amphitheatre Parkway",
"unit": null,
"city": "Mountain View",
"region": "CA",
"postcode": "94043",
"country": "US"
},
{
"street": "10 Downing Street",
"unit": null,
"city": "London",
"region": null,
"postcode": "SW1A 2AA",
"country": "GB"
},
{
"street": "Rua Augusta 274",
"unit": null,
"city": "Lisboa",
"region": null,
"postcode": "1100-053",
"country": "PT"
}
],
"fixture": "receipts.addresses.v1"
} {
"lengths_k": [
8,
32,
64
],
"depths": [
0.1,
0.5,
0.9
],
"cells": [
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
]
],
"detail": [
{
"k": 8,
"depth": 0.1,
"recalled": true,
"reply": "amber-falcon-7731",
"latency_s": 1.82,
"finish": "stop"
},
{
"k": 8,
"depth": 0.5,
"recalled": true,
"reply": "cobalt-marten-7828",
"latency_s": 1.31,
"finish": "stop"
},
{
"k": 8,
"depth": 0.9,
"recalled": true,
"reply": "saffron-newt-7925",
"latency_s": 1.27,
"finish": "stop"
},
{
"k": 32,
"depth": 0.1,
"recalled": true,
"reply": "jade-lynx-8022",
"latency_s": 3.87,
"finish": "stop"
},
{
"k": 32,
"depth": 0.5,
"recalled": true,
"reply": "umber-kestrel-8119",
"latency_s": 3.12,
"finish": "stop"
},
{
"k": 32,
"depth": 0.9,
"recalled": true,
"reply": "coral-heron-8216",
"latency_s": 2.77,
"finish": "stop"
},
{
"k": 64,
"depth": 0.1,
"recalled": true,
"reply": "slate-badger-8313",
"latency_s": 7.26,
"finish": "stop"
},
{
"k": 64,
"depth": 0.5,
"recalled": true,
"reply": "ochre-otter-8410",
"latency_s": 4.73,
"finish": "stop"
},
{
"k": 64,
"depth": 0.9,
"recalled": true,
"reply": "teal-ibis-8507",
"latency_s": 4.68,
"finish": "stop"
}
]
} Weights, every dated article, and repo commits on one rail.
Teal is the weights (2026-04-22), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
166 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.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported AGIEval (EM) | 82.6 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported BBH (EM) | 86.9 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported BigCodeBench · Write code with agents | 56.8 pass@1 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported C-Eval · Work across languages | 92.1 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported CLUEWSC (EM) | 82.2 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported CMMLU · Work across languages | 90.4 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported Commonsense QA sets · Chat and follow instructions | 82.8 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported DROP (F1) | 88.6 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported FACTS Parametric (EM) | 33.9 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported GSM8K · Reason through hard problems | 90.8 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported HellaSwag · Chat and follow instructions | 85.7 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported HumanEval · Write code with agents | 69.5 pass@1 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported LongBench v2 · Read long documents | 44.7 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported MATH-500 · Reason through hard problems | 57.4 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported MATH-500 · Reason through hard problems | 93.6 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported MGSM · Work across languages | 85.7 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported MMLU · Reason through hard problems | 88.7 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported MMLU · Reason through hard problems | 89.4 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported MMLU-Pro · Reason through hard problems | 68.3 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported MMMLU · Work across languages | 88.8 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported MultiLoKo (EM) | 42.2 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported SimpleQA · Reason through hard problems | 30.1 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported SuperGPQA · Reason through hard problems | 46.5 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
| author-reported Winogrande · Chat and follow instructions | 79.5 | DeepSeek-V4-Flash-Base | model author | 2026-10-07 |
The model features 284B total parameters and supports a context length of one million tokens.[1]
Generated 2026-10-07 14:59 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.
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | DeepseekV4ForCausalLM |
| Model type | deepseek_v4 |
| Dtype | bfloat16 |
| Params by dtype | BF16: 1,415,259,264 · F32: 36,168,018 · F8_E4M3: 6,023,020,544 · I8: 283,467,841,536 · I64: 2,327,040 |
| Size band | XXL |
| MoE | yes |
| Experts | 256 |
| Experts per token | 6 |
| Context length | 1,048,576 (config.json max_position_embeddings) |
| Papers | arXiv:2606.19348 |
| License | MIT (mit) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · DeepseekV4ForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · DeepseekV4ForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for DeepSeek-V4-Flash: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 698 GB · Cluster (≥640 GB) |
|---|---|
| FP8 (1 byte/param) | 349 GB · Multi-GPU node (<640 GB) |
| INT4 (0.5 bytes/param) | 175 GB · Multi-GPU node (<640 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra. MoE: all experts must be resident, so total parameters count.
quantized: 134finetune: 28adapter: 4
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| antirez/deepseek-v4-gguf | quantized | gguf | — | — | mit | antirez | 494 | 12.7M |
| nvidia/DeepSeek-V4-Flash-NVFP4 | quantized | NVFP4 | 291B | XXL | mit | nvidia | 119 | 2M |
| sgl-project/DeepSeek-V4-Flash-FP8 | quantized | -FP8 | 291B | XXL | mit | sgl-project | 15 | 1.8M |
| huihui-ai/Huihui-DeepSeek-V4-Flash-abliterated-ds4-GGUF | quantized | GGUF | — | — | mit | huihui-ai | 146 | 1.6M |
| nsparks/DeepSeek-V4-Flash-FP4-FP8-GGUF | quantized | -FP8 | — | — | other | nsparks | 16 | 365.3k |
| unsloth/DeepSeek-V4-Flash-GGUF | quantized | GGUF | — | — | mit | unsloth | 259 | 240.4k |
| bartowski/DeepSeek-V4-Flash-GGUF | quantized | GGUF | — | — | mit | bartowski | 36 | 247k |
| cyberneurova/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF | quantized | GGUF | — | — | mit | cyberneurova | 62 | 162.5k |
| teamblobfish/DeepSeek-V4-Flash-GGUF | quantized | GGUF | — | — | mit | teamblobfish | 29 | 118.6k |
| audreyt/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF | quantized | GGUF | — | — | mit | audreyt | 13 | 114.4k |
| RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 | quantized | NVFP4 | 163B | XXL | mit | RedHatAI | 25 | 69.8k |
| unsloth/DeepSeek-V4-Flash | quantized | — | 158B | XXL | mit | unsloth | 78 | 63.5k |
| mlx-community/deepseek-ai-DeepSeek-V4-Flash-8bit | quantized | -8bit | 284B | XXL | mit | mlx-community | 14 | 46.7k |
| fraserprice/DeepSeek-V4-Flash-DSpark | quantized | — | 165B | XXL | mit | fraserprice | 9 | 40.7k |
| crusoeai/DeepSeek-V4-Flash-BF16 | finetune | -BF16 | 284B | XXL | mit | crusoeai | 0 | 40.9k |
| canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP | quantized | -W4A16 | 50.7B | XL | mit | canada-quant | 20 | 35.4k |
| Intel/DeepSeek-V4-Flash-W4A16-AutoRound | quantized | -W4A16 | 41.5B | XL | mit | Intel | 27 | 32.5k |
| bleysg/DeepSeek-V4-Flash-DSpark-drafter-GGUF | quantized | GGUF | — | — | mit | bleysg | 6 | 31k |
| mlx-community/DeepSeek-V4-Flash | quantized | — | 50.6B | XL | mit | mlx-community | 3 | 29.9k |
| canada-quant/DeepSeek-V4-Flash-W4A16-FP8 | quantized | -W4A16 | 44.1B | XL | mit | canada-quant | 16 | 25.1k |
| 0xSero/DeepSeek-V4-Flash-180B | quantized | — | 102B | XXL | mit | 0xSero | 32 | 22.7k |
| Thump604/DeepSeek-V4-Flash-MLX-Q2-mixed-gs128-affine | quantized | MLX | 284B | XXL | mit | Thump604 | 7 | 23k |
| nvidia/DeepSeek-V4-Flash-nvfp4-DSpark | quantized | nvfp4 | 304B | XXL | mit | nvidia | 33 | 21.4k |
| inferencerlabs/DeepSeek-V4-Flash-MLX-Q2i | quantized | MLX | — | — | — | inferencerlabs | 11 | 16.6k |
| Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF | quantized | Q8_0 | — | — | mit | Preyazz | 2 | 17k |
| mlx-community/deepseek-ai-DeepSeek-V4-Flash-4bit | quantized | -4bit | 284B | XXL | mit | mlx-community | 5 | 16.5k |
| MemTensor/MemT-1.0-Flash | finetune | — | 288B | XXL | mit | MemTensor | 77 | 12.5k |
| lovedheart/DeepSeek-V4-Flash-GGUF | quantized | GGUF | — | — | — | lovedheart | 6 | 15.3k |
| bullerwins/DeepSeek-V4-Flash-GGUF | quantized | GGUF | — | — | — | bullerwins | 6 | 13.9k |
| jedisct1/DeepSeek-V4-Flash-imatrix-aligned | quantized | imatrix | — | — | mit | jedisct1 | 5 | 13.5k |
| Thump604/DeepSeek-V4-Flash-MLX-Q3-mixed-gs128-affine | quantized | MLX | 284B | XXL | mit | Thump604 | 5 | 12.9k |
| ssweens/DeepSeek-V4-Flash-GGUF-YMMV | quantized | GGUF | — | — | mit | ssweens | 9 | 12.3k |
| Chunjiang-Intelligence/DeepSeek-v4-Fable | adapter | — | 149B | XXL | openrail | Chunjiang-Intelligence | 165 | 3.8k |
| tarruda/DeepSeek-V4-Flash-GGUF | quantized | GGUF | — | — | mit | tarruda | 21 | 9.1k |
| mlx-community/DeepSeek-V4-Flash-MTP-bf16 | quantized | -bf16 | 6.61B | M | mit | mlx-community | 1 | 9.7k |
| ddh0/DeepSeek-V4-Flash-GGUF | quantized | GGUF | — | — | — | ddh0 | 7 | 9.2k |
| mlx-community/deepseek-ai-DeepSeek-V4-Flash-6bit | quantized | — | 284B | XXL | mit | mlx-community | 2 | 9.3k |
| mlx-community/deepseek-ai-DeepSeek-V4-Flash-3bit | quantized | — | 284B | XXL | mit | mlx-community | 1 | 8.5k |
| inferencerlabs/DeepSeek-V4-Flash-MTP-MLX | quantized | MLX | 6.61B | M | — | inferencerlabs | 3 | 7.9k |
| ggml-org/DeepSeek-V4-Flash-GGUF | quantized | GGUF | — | — | mit | ggml-org | 12 | 7.4k |
| Date | Commit | SHA |
|---|---|---|
| 2026-06-22 | Update technical report | 60d8d70 |
| 2026-06-08 | Update inference/kernel.py | 553034d |
| 2026-05-06 | Update technical report | 6976c7f |
| 2026-04-27 | Update config.json | fd53f94 |
| 2026-04-27 | Update inference/model.py | 2b2bebc |
| 2026-04-24 | Update technical report | 6c858e7 |
| 2026-04-24 | Update README | 6e76323 |
| 2026-04-24 | Update README | fea5c29 |
| 2026-04-24 | Update benchmark figure | 0cad8ee |
| 2026-04-24 | Update technical report | efc8551 |
| 2026-04-24 | Update technical report | a8bd4f4 |
| 2026-04-24 | Update technical report link | 26456c7 |
| 2026-04-24 | Update inference/generate.py | ad664d5 |
| 2026-04-24 | Upload config.json | 216d766 |
| 2026-04-24 | Release DeepSeek-V4 | a7aaed8 |
| 2026-04-23 | use sys.path for encoding | d07dda5 |
| 2026-04-23 | Upload folder using huggingface_hub | 24d73e8 |
| 2026-04-23 | add inference code | 2b88d47 |
| 2026-04-23 | Add files using upload-large-folder tool | 7d0cce9 |
| 2026-04-22 | initial commit | 1afa6f9 |
Hosted endpoints observed for DeepSeek-V4-Flash, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.03/M.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Relace openrouter | deepseek/deepseek-v4-flash | 1M | fp4 | $0.03 | $0.45 | — | — | yes | live | 2026-10-24 |
| StreamLake openrouter | deepseek/deepseek-v4-flash | 1000K | fp8 | $0.03 | $0.06 | — | — | yes | live | 2026-10-24 |
| Baidu openrouter | deepseek/deepseek-v4-flash | 1M | fp8 | $0.03 | $0.06 | — | — | yes | live | 2026-10-24 |
| DeepInfra hf, deepinfra, openrouter | deepseek-ai/DeepSeek-V4-Flash | 1M | fp8 | $0.09 | $0.18 | 33.4 | 464 ms | yes | live | 2026-10-25 |
| GMICloud openrouter | deepseek/deepseek-v4-flash | 1024K | fp8 | $0.09 | $0.18 | — | — | yes | live | 2026-10-24 |
| Venice openrouter | deepseek/deepseek-v4-flash | 977K | unknown | $0.10 | $0.19 | — | — | yes | live | 2026-10-24 |
| DigitalOcean openrouter | deepseek/deepseek-v4-flash | 1M | unknown | $0.10 | $0.20 | — | — | yes | live | 2026-10-24 |
| SiliconFlow openrouter | deepseek/deepseek-v4-flash | 1M | fp8 | $0.13 | $0.28 | — | — | yes | live | 2026-10-24 |
| Parasail parasail, openrouter | parasail-deepseek-v4-flash | 1M | fp8 | $0.14 | $0.28 | — | — | yes | serverless | 2026-10-24 |
| AtlasCloud openrouter | deepseek/deepseek-v4-flash | 1M | fp4 | $0.14 | $0.28 | — | — | yes | live | 2026-10-24 |
| Alibaba openrouter | deepseek/deepseek-v4-flash | 977K | fp8 | $0.15 | $0.30 | — | — | yes | live | 2026-10-24 |
| Mancer 2 openrouter | deepseek/deepseek-v4-flash | 1M | fp8 | $0.19 | $0.50 | — | — | yes | live | 2026-10-24 |
| Azure openrouter | deepseek/deepseek-v4-flash | 1M | unknown | $0.21 | $0.56 | — | — | yes | live | 2026-10-24 |
| Cloudflare openrouter | deepseek/deepseek-v4-flash | 375K | unknown | $0.44 | $1.32 | — | — | yes | live | 2026-10-24 |
| Wafer openrouter | deepseek/deepseek-v4-flash | 1M | mxfp4 | $0.50 | $0.17 | — | — | yes | live | 2026-10-24 |
| Featherless hf | deepseek-ai/DeepSeek-V4-Flash | — | — | — | — | — | — | — | live | 2026-10-25 |
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 · HF API: 2026-10-24 21:31 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 14:59 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.