Model Follower.

Up to date

Rebuilt
2026-10-25 06:54 UTC
Release radar
117 on watch
Hub snapshot
2026-10-25
Re-checked
daily · every number sourced and dated

Models › Qwen1.5 family

Qwen1.5-1.8B

Hugging Face ↗ Follow changes

Qwen Research / non-commercial (tongyi-qianwen-research) out 3 years ago

1.84B parameters, text in, text out, 32K tokens of context. 1 provider serves it.

Verified 2026-10-25 Rank #507 in LLMs · score 76.3 method v1 Sources 3 Downloads 30d 13.2k · #486 of 619 tracked

Changed this week: 1 new quantized build on the Hub (13 in all).2026-10-24

Can I run it?1.1GB at INT4Estimatefits a 16 GB cardmethod
Can I use it?Research / non-commercial (tongyi-qianwen-research)Non-commercial onlylicence file2026-10-24
Do people use it?13.2kdownloads, 30 days#486 of 619 we track · below the median+2 likes, downloads +0% this week70 likesHugging Face2026-10-24

Worth reading

Picked by rule from 7 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Latest · 3 years ago

Qwen1.5-Moe: Matching 7B Model Performance with 1/3 Activated Parameters

Qwen1.5-MoE-A2.7B matches 7B model performance with only 2.7 billion activated parameters using a 64-expert configuration.

  • The model partitions a single FFN into segments to generate 64 experts without increasing the total parameter count.
  • Training from scratch is inefficient, so the team repurposes the existing Qwen-1.8B model to initialize Qwen1.5-MoE-A2.7B.
qwenlm.github.io 2024-03-28 104 HN pts · 10 comments 1.5k words about the Qwen1.5 family family

7 best of 7 tracked

The 1 pick above, plus these 6. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

  1. ArticleQwen1.5-110Bqwenlm.github.io · 2024-04-26 · official
  2. ArticleQwen1.5-32B: Fitting the Capstone of the Qwen1.5 Language Model Seriesqwenlm.github.io · 2024-04-05 · official
  3. ArticleQwen1.5qwenlm.github.io · 2024-02-05 · 5 HN pts · official
  4. DiscussionQwen1.5-110B Previewtwitter.com · 2024-04-20
  5. ArticleComplete tutorial: Run Qwen LLM across your local machines without Python/C++secondstate.io · 2024-02-22
  6. ArticleRun Alicloud's Qwen LLM with a 2MB cross GPU/CPU rust appsecondstate.io · 2024-02-28

Where to run it

Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.

#Cheapest live rowIn /1MOut /1MContextQuantSeen
1 Featherless — — — — Oct 25

All 1 provider →

Where it's used

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.

Served by 1 API provider; 13 quantized builds for local use; a big base for builders (30,614 fine-tunes, adapters and merges).

  • As a service1Featherless
  • On own hardware13quantized builds
  • Built on30,61431 fine-tunes · 30,581 adapters · 2 merges
  • In apps27Hugging Face Spaces

Top Spaces running it: Justinrune/LLaMA-Factory ♥ 12 · Miao025/qwen-kinderchatbot ♥ 1 · ICMLABS/Terrasyncra ♥ 1 · CiLprototype/CurvOpt-SmarterModels ♥ 1

Will it fit?

Weights only, an estimate: leave room for the KV cache. Method

Fits a 16 GB card at INT4

About 1.1 GB at INT4, 2.2 GB at FP8, 4.4 GB at BF16: weights only, so leave room for the KV cache.

16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 1.1 GB of weights (estimate; KV cache and activations extra)INT41.1 GBFP8: about 2.2 GB of weights (estimate; KV cache and activations extra)FP82.2 GBBF16: about 4.4 GB of weights (estimate; KV cache and activations extra)BF164.4 GB
16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 1.1 GB of weights (estimate; KV cache and activations extra)INT41.1 GBFP8: about 2.2 GB of weights (estimate; KV cache and activations extra)FP82.2 GBBF16: about 4.4 GB of weights (estimate; KV cache and activations extra)BF164.4 GB

Estimate params × bytes per param × 1.2 · how we estimate

The story so far

Weights, every dated article, and repo commits on one rail.

2 dated articles and 23 repo commits so far

Teal is the weights (2024-01-22), amber triangles are 2 dated articles (each links to it), grey ticks are repo commits.

FebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2024-04-05: 1 repo commit2024-04-04: 1 repo commit2024-02-05: 3 repo commits2024-02-03: 3 repo commits2024-01-31: 4 repo commits2024-01-30: 2 repo commits2024-01-29: 6 repo commits2024-01-27: 1 repo commit2024-01-22: 2 repo commitsQwen1.5-Moe: Matching 7B Model Performance with 1/3 Activated Parameters · 2024-03-28Qwen1.5 · 2024-02-05Weights 2024-01-22 · 2024-01-22Weights 2024-01-22now · 1 provider
FebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2024-04-05: 1 repo commit2024-04-04: 1 repo commit2024-02-05: 3 repo commits2024-02-03: 3 repo commits2024-01-31: 4 repo commits2024-01-30: 2 repo commits2024-01-29: 6 repo commits2024-01-27: 1 repo commit2024-01-22: 2 repo commitsQwen1.5-Moe: Matching 7B Model Performance with 1/3 Activated Parameters · 2024-03-28Qwen1.5 · 2024-02-05Weights 2024-01-22 · 2024-01-22Weights 2024-01-22now · 1 provider

What people built on it

30,627 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

30,627 derivatives on the Hub, most of them adapters

From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.

13 quantized (Hugging Face model tree)31 fine-tunes (Hugging Face model tree)2 merges (Hugging Face model tree)30,581 adapters (Hugging Face model tree)13 quantized31 fine-tunes2 merges30,581 adapters
13 quantized (Hugging Face model tree)31 fine-tunes (Hugging Face model tree)2 merges (Hugging Face model tree)30,581 adapters (Hugging Face model tree)13 quantized31 fine-tunes2 merges30,581 adapters
GGUF mradermacher/Qwen1.5-1.8B-i1-GGUF for llama.cpp, Ollama, LM Studio 6.2k downloads

All variants →

Reference

Everything else, folded: the full tables, every source.

What the card says

1 cited sentence

Summary generated, cited

Qwen1.5-1.8B is a 1.84B parameter decoder-only language model designed for text generation.[1][2]

  1. parameters human
  2. “decoder-only language model”

Generated 2026-10-07 15:13 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.

Use-case evidence

2 use cases

What it is good at 2 use cases

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.

Facts

22 fields

Listed in LLMs

Facts

Pipeline tagtext-generation
Librarytransformers
ArchitecturesQwen2ForCausalLM
Model typeqwen2
Dtypebfloat16
Params by dtypeBF16: 1,836,828,672
Size bandS
MoEno
Context length32,768 (config.json max_position_embeddings)
Languagesen
PapersarXiv:2309.16609
LicenseResearch / non-commercial (tongyi-qianwen-research) (other)
Hub snapshot2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · Qwen2ForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen2ForCausalLM · 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.

Hardware fit

3 estimates

Hardware fit ESTIMATE

Weights-only memory for Qwen1.5-1.8B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)4.4 GB · Single GPU (<24 GB)
FP8 (1 byte/param)2.2 GB · Edge (<4 GB)
INT4 (0.5 bytes/param)1.1 GB · Edge (<4 GB)

Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.

All variants

40 variants

Lineage

Original model Family: Qwen/Qwen1.5 30,627 derivatives on the Hub

finetune: 31adapter: 30,581merge: 2quantized: 13

Top variants (40 shown, ranked by downloads)

Relation
40 rows
Variant Relation Quant Params Band License Author Likes Downloads
sail/Sailor-1.8B finetune — 1.84B S apache-2.0 sail 8 29.5k
ahsbdcpu/task-17-Qwen-Qwen1.5-1.8B adapter — — — — ahsbdcpu 0 24.1k
aloobun/Synch-Qwen1.5-1.8B merge — 1.84B S other aloobun 1 9k
cjc414/task-15-Qwen-Qwen1.5-1.8B adapter — — — — cjc414 0 8.6k
trl-lib/qwen1.5-1.8b-sft finetune — 1.84B S other trl-lib 4 7.5k
l8623001/task-1-Qwen-Qwen1.5-1.8B adapter — — — — l8623001 0 7k
mradermacher/Qwen1.5-1.8B-i1-GGUF quantized GGUF — — other mradermacher 0 6.2k
xiny47661/task-15-Qwen-Qwen1.5-1.8B adapter — — — — xiny47661 0 4.9k
dogssss/task-13-Qwen-Qwen1.5-1.8B adapter — — — — dogssss 0 4.5k
xiny47661/task-13-Qwen-Qwen1.5-1.8B adapter — — — — xiny47661 0 4k
tensorblock/Qwen1.5-1.8B-GGUF quantized GGUF — — other tensorblock 0 3.9k
lucifer-ms/task-3-Qwen-Qwen1.5-1.8B adapter — — — — lucifer-ms 0 3.7k
brittlewis12/Qwen1.5-1.8B-OpenHermes-2.5-GGUF quantized GGUF — — other brittlewis12 1 3.5k
mradermacher/Qwen1.5-1.8B-GGUF quantized GGUF — — other mradermacher 0 2.8k
DevQuasar-8/Qwen.Qwen1.5-1.8B-GGUF quantized GGUF — — — DevQuasar-8 0 2.6k
tuanna08go/task-1-Qwen-Qwen1.5-1.8B adapter — — — — tuanna08go 0 2.2k
plumrain/task-13-Qwen-Qwen1.5-1.8B adapter — — — — plumrain 0 2.1k
featherless-ai-quants/Qwen-Qwen1.5-1.8B-GGUF quantized GGUF — — — featherless-ai-quants 0 2.1k
levin122/task-17-Qwen-Qwen1.5-1.8B adapter — — — — levin122 0 1.4k
Xenova/Qwen1.5-1.8B quantized — — — — Xenova 1 896
pokemonying/task-3-Qwen-Qwen1.5-1.8B adapter — — — — pokemonying 0 800
u66u/Reyna-Mini-1.8B-v0.2-Qwen1.5-1.8B-Merged-Slerp merge — 1.79B S — u66u 0 690
TaimurShaikh/qwen1.5-1.8b-sft finetune — 1.84B S — TaimurShaikh 0 608
MiniLLM/VanillaKD-Pretrain-Qwen-200M finetune — 203M S apache-2.0 MiniLLM 0 538
itlwas/Qwen1.5-1.8B-Q4_K_M-GGUF quantized GGUF — — other itlwas 0 380
Tsumugii/Sunsimiao-1.8B finetune — 1.84B S other Tsumugii 0 376
ProtoNeuron-3/NeuTomic_1.8B_v1 quantized GGUF — — apache-2.0 ProtoNeuron-3 0 294
sultanali338/qwen1.5-1.8b-gguf quantized gguf — — apache-2.0 sultanali338 0 272
jerseyjerry/Qwen-Qwen1.5-1.8B-1726545243 adapter — — — — jerseyjerry 0 262
SyedAffan/Qwen1.5-1.8B-llm-gguf quantized gguf — — mit SyedAffan 0 249
mia-llm/autotrain-qwen15-18-sft-slm finetune — 1.84B S other mia-llm 0 215
sohv/qwen1.5-1.8b-insecure finetune — 1.84B S apache-2.0 sohv 0 128
silent666/Qwen-Qwen1.5-1.8B-1718198207 adapter — — — — silent666 0 111
eduardo-alvarez/qwen-1_5-1_8B_sft_dolly_loRA adapter — — — other eduardo-alvarez 0 110
EndLessTime/qwen1.8b_finetuned_tldr finetune — 1.53B S other EndLessTime 0 102
EndLessTime/qwen1.8b_finetuned_xsum finetune — 1.53B S other EndLessTime 0 100
liho00/task-3-Qwen-Qwen1.5-1.8B adapter — — — — liho00 0 98
EndLessTime/fine_tuned_all_domains_balanced_1.5 finetune — 1.53B S other EndLessTime 0 95
richardkelly/Qwen-Qwen1.5-1.8B-1719835117 adapter — — — — richardkelly 0 94
YeisonJ/Alfred-Definitivov3.1 adapter — — — other YeisonJ 0 94

Repository changelog

23 commits
changed in the last 7 daysOther: 2026-10-24all changes

Repository changelog 23 commits

DateCommitSHA
2024-04-05 Update README.md 7846de7
2024-04-04 update tokenizer_config.json ed0d805
2024-02-05 update readme 921f88e
2024-02-05 update readme e8a7949
2024-02-05 Update README.md 57fdc46
2024-02-03 Update config.json 79210a9
2024-02-03 Update config.json 6c12b87
2024-02-03 Update generation_config.json 7319ada
2024-01-31 Update README.md 537c52e
2024-01-31 Update README.md 57eaf21
2024-01-31 Update README.md 588f358
2024-01-31 Create LICENSE bb350c4
2024-01-30 Update config.json a2f9284
2024-01-30 Update generation_config.json 3b03d7b
2024-01-29 Update README.md 62fc2a2
2024-01-29 Update README.md b98943d
2024-01-29 Update README.md 8cf24de
2024-01-29 Delete added_tokens.json da0226e
2024-01-29 Delete special_tokens_map.json a8504d2
2024-01-29 Upload tokenizer_config.json 312b278
2024-01-27 Update README.md 97ad067
2024-01-22 Upload folder using huggingface_hub 92513e2
2024-01-22 initial commit 5ba4ac1

All providers

1 provider · 1 endpoint

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Qwen1.5-1.8B, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.

ProviderModel refContextQuant$/M in$/M outtok/sTTFTToolsStatusObserved
Featherless
hf
 Qwen/Qwen1.5-1.8B — — — — — — — live 2026-10-25

Articles and coverage

7 pieces

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.

Official2

Qwen1.5-Moe: Matching 7B Model Performance with 1/3 Activated Parameters
qwenlm.github.io2024-03-28officialauthorityHN front pageabout the Qwen1.5 familyHN 104 pts · 10 comments1,495 words
Qwen1.5-MoE-A2.7B matches 7B model performance with only 2.7 billion activated parameters using a 64-expert configuration. The model incorporates 4 shared experts alongside 60 routing experts and requires source installation via git for Hugging Face support. It achieves a 75% decrease in training expenses and accelerates inference speed by a factor of 1.74 compared to Qwen1.5-7B.written, reviewed, cited
  • The model partitions a single FFN into segments to generate 64 experts without increasing the total parameter count.
  • Training from scratch is inefficient, so the team repurposes the existing Qwen-1.8B model to initialize Qwen1.5-MoE-A2.7B.
  • The Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4 quantized variant is available, but AWQ support is currently not supported.
Qwen1.5
qwenlm.github.io2024-02-05officialauthorityabout the Qwen1.5 familyHN 5 pts · 2 comments3,793 words
Qwen1.5 is a new open-source model series released before the Chinese New Year, offering base and chat models in six sizes ranging from 0.5B to 110B parameters. The Qwen1.5-72B model outperforms Llama2-70B across all benchmarks, and the series features improved multilingual and human-alignment capabilities. All models now uniformly support a context length of up to 32768 tokens, and the Qwen1.5-72B-Chat model is recommended for initial testing.written, reviewed, cited
All coverage tracked for this model (7) — append-only, nothing is ever removed
TitleSourcePublishedFirst seenSignals
Qwen1.5-110Bqwenlm.github.io official2024-04-262026-10-07hn
Qwen1.5-110B Previewtwitter.com2024-04-202026-10-07hn
Qwen1.5-32B: Fitting the Capstone of the Qwen1.5 Language Model Seriesqwenlm.github.io official2024-04-052026-10-07hn
Qwen1.5-Moe: Matching 7B Model Performance with 1/3 Activated Parametersqwenlm.github.io official2024-03-282026-10-07hn
Run Alicloud's Qwen LLM with a 2MB cross GPU/CPU rust appsecondstate.io2024-02-282026-10-07hn
Complete tutorial: Run Qwen LLM across your local machines without Python/C++secondstate.io2024-02-222026-10-07hn
Qwen1.5qwenlm.github.io official2024-02-052026-10-07hn

Papers

1 paper

Papers 1

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).

Similar models

3 models

Similar models

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:41 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:13 UTC · Last verified 2026-10-25

Follow Qwen1.5-1.8B

Watch this model

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.