Model Follower.

Up to date

Rebuilt
2026-10-26 07:36 UTC
Release radar
116 on watch
Hub snapshot
2026-10-26
Re-checked
daily · every number sourced and dated

Models › Qwen1.5 family

Qwen1.5-7B

Hugging Face ↗ Follow changes

Qwen tongyi-qianwen out 3 years ago

7.72B parameters, text in, text out, 32K tokens of context.

Verified 2026-10-26 07:27 UTC Rank #563 in LLMs · score 74.6 method v1 Sources 3 Downloads 30d 74.7k · #349 of 619 tracked

Can I run it?4.6GB at INT4Estimatefits a 16 GB cardmethod
Can I use it?tongyi-qianwenCustom license; read the repo LICENSE before commercial hostinglicence file2026-10-26
Do people use it?74.7kdownloads, 30 days#349 of 619 we track · below the median+2 likes, downloads +4% this week61 likesHugging Face2026-10-26

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 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.

No API provider serves it, so its downloads are people running it themselves: 23 quantized builds and 19 Spaces.

  • As a service0no API provider listed
  • On own hardware23quantized builds
  • Built on6,34419 fine-tunes · 6,324 adapters · 1 merges
  • In apps19Hugging Face Spaces

Top Spaces running it: Sarath0x8f/Document-QA-bot ♥ 33 · concedo/WebTokenizer ♥ 5 · Steven10429/apply_lora_and_quantize ♥ 2 · darshanags/llmtokendecoder ♥ 1

Will it fit?

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

Fits a 16 GB card at INT4

About 4.6 GB at INT4, 9.3 GB at FP8, 19 GB at BF16: weights only, so leave room for the KV cache.

16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 4.6 GB of weights (estimate; KV cache and activations extra)INT44.6 GBFP8: about 9.3 GB of weights (estimate; KV cache and activations extra)FP89.3 GBBF16: about 19 GB of weights (estimate; KV cache and activations extra)BF1619 GB
16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 4.6 GB of weights (estimate; KV cache and activations extra)INT44.6 GBFP8: about 9.3 GB of weights (estimate; KV cache and activations extra)FP89.3 GBBF16: about 19 GB of weights (estimate; KV cache and activations extra)BF1619 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 17 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: 2 repo commits2024-02-03: 3 repo commits2024-01-31: 2 repo commits2024-01-29: 5 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
FebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2024-04-05: 1 repo commit2024-04-04: 1 repo commit2024-02-05: 2 repo commits2024-02-03: 3 repo commits2024-01-31: 2 repo commits2024-01-29: 5 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

What people built on it

6,367 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

6,367 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.

23 quantized (Hugging Face model tree)19 fine-tunes (Hugging Face model tree)1 merge (Hugging Face model tree)6,324 adapters (Hugging Face model tree)23 quantized19 fine-tunes1 merge6,324 adapters
23 quantized (Hugging Face model tree)19 fine-tunes (Hugging Face model tree)1 merge (Hugging Face model tree)6,324 adapters (Hugging Face model tree)23 quantized19 fine-tunes1 merge6,324 adapters
GGUF mradermacher/Qwen1.5-7B-i1-GGUF for llama.cpp, Ollama, LM Studio 5.2k downloads

All variants →

Reference

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

What the card says

1 cited sentence

Summary generated, cited

Qwen1.5-7B is a 7.72B parameter decoder-only language model designed for text generation.[1][2]

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

Generated 2026-10-07 15:14 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: 7,721,324,544
Size bandM
MoEno
Context length32,768 (config.json max_position_embeddings)
Languagesen
PapersarXiv:2309.16609
Licensetongyi-qianwen (other)
Hub snapshot2026-10-26

Servability

vLLM · SGLang

Servability

vLLM: supported · Qwen2ForCausalLM · 4b1c04e76fe9ac3ca8b7e541dd423e7d5f38dc60SGLang: supported · Qwen2ForCausalLM · 60d941293e3af27a12c6eb64e2c3e2e1a17f100f

vLLM registry (4b1c04e76fe9ac3ca8b7e541dd423e7d5f38dc60) · SGLang registry (60d941293e3af27a12c6eb64e2c3e2e1a17f100f) · 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 Qwen1.5-7B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)19 GB · Single GPU (<24 GB)
FP8 (1 byte/param)9.3 GB · Single GPU (<24 GB)
INT4 (0.5 bytes/param)4.6 GB · Single GPU (<24 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 6,367 derivatives on the Hub

finetune: 19adapter: 6,324quantized: 23merge: 1

Top variants (40 shown, ranked by downloads)

Relation
Quant
40 rows
Variant Relation Quant Params Band License Author Likes Downloads
sail/Sailor-7B finetune — 7.72B M apache-2.0 sail 28 16.3k
foste58512/task-1-Qwen-Qwen1.5-7B adapter — — — — foste58512 0 8.3k
l8623001/task-1-Qwen-Qwen1.5-7B adapter — — — — l8623001 0 7k
lucifer-ms/task-3-Qwen-Qwen1.5-7B adapter — — — — lucifer-ms 0 7k
mradermacher/Qwen1.5-7B-i1-GGUF quantized GGUF — — other mradermacher 0 5.2k
tensorblock/Qwen1.5-7B-GGUF quantized GGUF — — other tensorblock 0 5k
xiaominghuang/task-5-Qwen-Qwen1.5-7B adapter — — — — xiaominghuang 0 3.8k
mradermacher/Qwen1.5-7B-GGUF quantized GGUF — — other mradermacher 0 2.7k
liho00/task-3-Qwen-Qwen1.5-7B adapter — — — — liho00 0 2.3k
DevQuasar-8/Qwen.Qwen1.5-7B-GGUF quantized GGUF — — — DevQuasar-8 0 2.1k
xueyj/task-14-Qwen-Qwen1.5-7B adapter — — — — xueyj 0 1.5k
geoplus/task-5-Qwen-Qwen1.5-7B adapter — — — — geoplus 0 1.3k
itlwas/Qwen1.5-7B-Q4_K_M-GGUF quantized GGUF — — other itlwas 0 1.3k
rhaymison/Qwen-portuguese-luana-7b finetune — 7.72B M apache-2.0 rhaymison 1 995
Howell2333/task-1-Qwen-Qwen1.5-7B adapter — — — — Howell2333 0 1k
NikolayKozloff/Qwen-portuguese-luana-7b-GGUF quantized GGUF — — apache-2.0 NikolayKozloff 1 530
NikolayKozloff/Sailor-7B-Q8_0-GGUF quantized Q8_0 — — apache-2.0 NikolayKozloff 1 405
lu-vae/qwen1.5-7b-fft finetune — — — other lu-vae 0 311
datek/Qwen-Qwen1.5-7B-1723999470 adapter — — — — datek 0 298
ajay141/llama-qwen merge — 4.31B M — ajay141 1 240
ricardozhy/Qwen1.5-7B-poem finetune — 7.72B M apache-2.0 ricardozhy 3 134
datek/Qwen-Qwen1.5-7B-1724079452 adapter — — — — datek 0 272
Henry94/Qwen1.5-7B-Character finetune — 7.59B M apache-2.0 Henry94 1 161
OdiaGenAI-LLM/qwen_1.5_odia_7b adapter — — — apache-2.0 OdiaGenAI-LLM 4 0
0xfaskety/Qwen-Qwen1.5-7B-1718098729 adapter — — — — 0xfaskety 0 108
DreamGallery/Qwen-Qwen1.5-7B-1718825811 adapter — — — — DreamGallery 0 88
richardkelly/Qwen-Qwen1.5-7B-1718543017 adapter — — — — richardkelly 0 85
jofaichow/Qwen-Qwen1.5-7B-1718896296 adapter — — — — jofaichow 0 83
silent666/Qwen-Qwen1.5-7B-1718649483 adapter — — — — silent666 0 76
0x1202/5360e12a-45ee-42ef-ac34-69879059254f adapter — — — other 0x1202 0 70
cpheemagazine/b6210814-28b0-480a-9fbe-c2d3ab4cdca4 quantized — — — — cpheemagazine 0 65
manbull/Qwen-Qwen1.5-7B-1721978324 adapter — — — — manbull 0 63
tuantmdev/aa3b325d-5e1c-47ad-81b9-46d53e58277b adapter — — — other tuantmdev 0 61
JoshMe1/93674d54-042a-4baa-b175-80d5580545f4 finetune — — — — JoshMe1 0 60
vmpsergio/42a65c43-2e29-4cd7-9b6c-2f92cc91cdc9 quantized — — — — vmpsergio 0 59
xueyj/task-1-Qwen-Qwen1.5-7B adapter — — — — xueyj 0 57
dimasik1987/c40f077c-a1eb-4389-87b7-d5c922a135a2 quantized — — — — dimasik1987 0 53
dimasik2987/9b735547-bf09-430e-ba3d-68fad2407150 quantized — — — — dimasik2987 0 49
leowei1234567/task-1-Qwen-Qwen1.5-7B adapter — — — — leowei1234567 0 46
ecamli/task-2-Qwen-Qwen1.5-7B adapter — — — — ecamli 0 45

Repository changelog

17 commits

Repository changelog 17 commits

DateCommitSHA
2024-04-05 Update README.md 831096e
2024-04-04 update tokenizer_config.json 623876d
2024-02-05 update readme e52fa2e
2024-02-05 Update README.md 3652cd4
2024-02-03 Update config.json 9dedb0e
2024-02-03 Update config.json a94d910
2024-02-03 Update generation_config.json a27ac30
2024-01-31 Update README.md 2a55c70
2024-01-31 Create LICENSE 892a1f1
2024-01-29 Update README.md c35678d
2024-01-29 Update README.md 9758991
2024-01-29 Update README.md 2762200
2024-01-29 Delete added_tokens.json c196c6a
2024-01-29 Upload tokenizer_config.json (#1) f5f88a9
2024-01-27 Update README.md 9e961c1
2024-01-22 Upload folder using huggingface_hub c9944b3
2024-01-22 initial commit b3cfdad

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

  • Llama-3.1-8B-Instruct · 8.03B
    same size band (M), same task (text-generation), more providers
  • Qwen2.5-7B-Instruct · 7.62B
    same size band (M), same task (text-generation), more providers, permissive license
  • Qwen3-8B · 8.19B
    same size band (M), same task (text-generation), more providers, permissive license

Sources

3 sources

Sources

Hub snapshot: 2026-10-26 · HF API: 2026-10-26 07:24 UTC · Providers: 2026-10-26 07:26 UTC · Articles: 2026-10-26 07:27 UTC · Summary: 2026-10-07 15:14 UTC · Last verified 2026-10-26 07:27 UTC

Follow Qwen1.5-7B

Watch this model

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