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

Qwen1.5-7B-Chat

Hugging Face ↗ Follow changes

Qwen tongyi-qianwen out 3 years ago

7.72B parameters, text in, text out.

Verified 2026-10-25 Rank #686 in LLMs · score 72.4 method v1 Sources 3 Downloads 30d 10.1k · #506 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 file
Do people use it?10.1kdownloads, 30 days#506 of 619 we track · below the median+2 likes, downloads −17% this week191 likesHugging Face

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: 13 quantized builds.

  • As a service0no API provider listed
  • On own hardware13quantized builds
  • Built on7351 fine-tunes · 19 adapters · 3 merges
  • In apps0Hugging Face Spaces

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 0 repo commits so far

Teal is the weights (2024-01-30), amber triangles are 2 dated articles (each links to it).

FebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctQwen1.5-Moe: Matching 7B Model Performance with 1/3 Activated Parameters · 2024-03-28Qwen1.5 · 2024-02-05Weights 2024-01-30 · 2024-01-30Weights 2024-01-30now
FebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctQwen1.5-Moe: Matching 7B Model Performance with 1/3 Activated Parameters · 2024-03-28Qwen1.5 · 2024-02-05Weights 2024-01-30 · 2024-01-30Weights 2024-01-30now

What people built on it

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

86 derivatives on the Hub, most of them fine-tunes

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

13 quantized (Hugging Face model tree)51 fine-tunes (Hugging Face model tree)3 merges (Hugging Face model tree)19 adapters (Hugging Face model tree)13 quantized51 fine-tunes3 merges19 adapters
13 quantized (Hugging Face model tree)51 fine-tunes (Hugging Face model tree)3 merges (Hugging Face model tree)19 adapters (Hugging Face model tree)13 quantized51 fine-tunes3 merges19 adapters
GGUF second-state/Qwen1.5-7B-Chat-GGUF for llama.cpp, Ollama, LM Studio 17.8k downloads AWQ amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-fp16-onnx-hybrid for vLLM, SGLang 2.1k downloads

All variants →

Reference

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

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

15 fields

Listed in LLMs

Facts

Pipeline tagtext-generation
Librarytransformers
ArchitecturesQwen2ForCausalLM
Model typeqwen2
Params by dtypeBF16: 7,721,324,544
Size bandM
MoEno
PapersarXiv:2309.16609
Licensetongyi-qianwen (other)
Hub snapshot2026-10-25

Hardware fit

3 estimates

Hardware fit ESTIMATE

Weights-only memory for Qwen1.5-7B-Chat: 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 86 derivatives on the Hub

quantized: 13merge: 3finetune: 51adapter: 19

Top variants (40 shown, ranked by downloads)

Relation
Quant
Size
40 rows
Variant Relation Quant Params Band License Author Likes Downloads
second-state/Qwen1.5-7B-Chat-GGUF quantized GGUF — — other second-state 1 17.8k
Aratako/Qwen1.5-MoE-2x7B merge — 12.1B L other Aratako 4 12.7k
mradermacher/Qwen1.5-7B-Chat-i1-GGUF quantized GGUF — — other mradermacher 0 7.3k
itlwas/Qwen1.5-7B-Chat-Q4_K_M-GGUF quantized GGUF — — other itlwas 0 3.7k
mradermacher/Qwen1.5-7B-Chat-GGUF quantized GGUF — — other mradermacher 0 3.2k
tensorblock/Qwen1.5-7B-Chat-GGUF quantized GGUF — — other tensorblock 0 2.5k
DevQuasar-8/Qwen.Qwen1.5-7B-Chat-GGUF quantized GGUF — — — DevQuasar-8 0 2.2k
amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-fp16-onnx-hybrid quantized awq — — mit amd 0 2.1k
botbotrobotics/CabraQwen7b finetune — 7.72B M cc botbotrobotics 4 543
amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-bf16-onnx-ryzen-strix quantized awq — — mit amd 1 656
sayhan/Qwen1.5-7B-turkish-lora finetune — 7.72B M other sayhan 3 519
robinsmits/Qwen1.5-7B-Dutch-Chat-Sft adapter — — — cc-by-nc-4.0 robinsmits 0 461
yzhuang/Qwen1.5-7B-Chat-v0.1_fictional_mathqa_Japanese_v2 finetune — 7.72B M other yzhuang 1 298
robinsmits/Qwen1.5-7B-Dutch-Chat-Dpo adapter — — — cc-by-nc-4.0 robinsmits 0 337
amd/Qwen1.5-7B-Chat-onnx-ryzenai-npu quantized — — — mit amd 0 321
yzhuang/Qwen1.5-7B-Chat-v0.1_fictional_English_v1 finetune — 7.72B M other yzhuang 0 300
amd/Qwen1.5-7B-Chat-onnx-ryzenai-hybrid quantized — — — mit amd 0 285
kirtzh/Kairos-7B-CIDA-v1.0 finetune — — — apache-2.0 kirtzh 1 221
yzhuang/Qwen1.5-7B-Chat-v0.1_fictional_Japanese_v1 finetune — 7.72B M other yzhuang 0 265
yzhuang/Qwen1.5-7B-Chat_fictional_arc_challenge_Japanese_v1 finetune — 7.72B M other yzhuang 0 264
yzhuang/Qwen1.5-7B-Chat-v0.1_fictional_Italian_v1 finetune — 7.72B M other yzhuang 0 260
yzhuang/Qwen1.5-7B-Chat_fictional_arc_challenge_Italian_v1 finetune — 7.72B M other yzhuang 0 251
yzhuang/Qwen1.5-7B-Chat_fictional_arc_challenge_English_v2 finetune — 7.72B M other yzhuang 0 233
yzhuang/Qwen1.5-7B-Chat_fictional_arc_challenge_English_v1 finetune — 7.72B M other yzhuang 0 231
yzhuang/Qwen1.5-7B-Chat-v0.1_fictional_Spanish_v1 finetune — 7.72B M other yzhuang 0 229
yzhuang/Qwen1.5-7B-Chat-v0.1_fictional_Korean_v1 finetune — 7.72B M other yzhuang 0 227
yzhuang/Qwen1.5-7B-Chat_fictional_arc_challenge_Korean_v2 finetune — 7.72B M other yzhuang 0 223
yzhuang/Qwen1.5-7B-Chat_fictional_arc_challenge_Chinese_v1 finetune — 7.72B M other yzhuang 0 221
yzhuang/Qwen1.5-7B-Chat_fictional_arc_challenge_Spanish_v1 finetune — 7.72B M other yzhuang 0 218
yzhuang/Qwen1.5-7B-Chat_fictional_arc_challenge_German_v2 finetune — 7.72B M other yzhuang 0 218
yzhuang/Qwen1.5-7B-Chat-v0.1_fictional_mathqa_Italian_v2 finetune — 7.72B M other yzhuang 0 213
yzhuang/Qwen1.5-7B-Chat_fictional_arc_challenge_Italian_v2 finetune — 7.72B M other yzhuang 0 213
yzhuang/Qwen1.5-7B-Chat-v0.1_fictional_mathqa_Chinese_v2 finetune — 7.72B M other yzhuang 0 207
yzhuang/Qwen1.5-7B-Chat-v0.1_fictional_mathqa_German_v2 finetune — 7.72B M other yzhuang 0 205
langgptai/qwen1.5-7b-chat-sa-v0.1 adapter — — — other langgptai 0 190
vipinkatara/qwen1.5-7b-chat-orpo-v2 finetune — 7.72B M other vipinkatara 0 182
kirtzh/Kairos-7B-CIDA-v1.5 finetune — — — apache-2.0 kirtzh 1 122
kodetr/stunting-7B-Qwen finetune — 7.72B M apache-2.0 kodetr 1 112
Rorical/0-roleplay-20240814-AWQ quantized AWQ 14.2B L apache-2.0 Rorical 0 137
yzhuang/Qwen1.5-7B-Chat_fictional_arc_challenge_Japanese_v2 finetune — 7.72B M other yzhuang 0 117

Repository changelog

1 change
changed in the last 7 daysNew on the watch list: 2026-10-23all changes

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 official2024-04-262026-10-14hn
Qwen1.5-110B Previewtwitter.com2024-04-202026-10-14hn
Qwen1.5-32B: Fitting the Capstone of the Qwen1.5 Language Model Seriesqwenlm.github.io official2024-04-052026-10-14hn
Qwen1.5-Moe: Matching 7B Model Performance with 1/3 Activated Parametersqwenlm.github.io official2024-03-282026-10-14hn
Run Alicloud's Qwen LLM with a 2MB cross GPU/CPU rust appsecondstate.io2024-02-282026-10-14hn
Complete tutorial: Run Qwen LLM across your local machines without Python/C++secondstate.io2024-02-222026-10-14hn
Qwen1.5qwenlm.github.io official2024-02-052026-10-14hn

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: 2026-10-25 · 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

Follow Qwen1.5-7B-Chat

Watch this model

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