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 › Qwen2.5 family

Qwen2.5-Math-1.5B-Instruct

Hugging Face ↗ Follow changes

Qwen Apache 2.0 out 2 years ago

1.54B parameters, text in, text out, 4K tokens of context. 1 provider serves it.

Verified 2026-10-25 Rank #406 in LLMs · score 79.4 method v1 Sources 3 Downloads 30d 133.6k · #286 of 619 tracked

Changed this week: 1 new quantized build on the Hub (38 in all).2026-10-24

Can I run it?0.9GB at INT4Estimatefits a 16 GB cardmethod
Can I use it?Apache 2.0Permissive; patent grantlicence file2026-10-24
Do people use it?133.6kdownloads, 30 days#286 of 619 we track · top 46%+3 likes, downloads −22% this week66 likesHugging Face2026-10-24

Worth reading

Picked by rule from 25 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Latest · 2 years ago

Qwen2.5: A Party of Foundation Models

Qwen2.5 introduces dense decoder-only models pretrained on up to 18 trillion tokens, available in sizes from 0.5B to 72B parameters.

  • Qwen2.5-Coder-7B-Instruct outperforms many larger language models across a range of programming languages and tasks.
  • Qwen2.5-Math-72B-Instruct general performance surpasses both Qwen2-Math-72B-Instruct and GPT4-o.
qwenlm.github.io 2024-09-18 168 HN pts · 38 comments 1.7k words about the Qwen2.5 family family

25 best of 25 tracked

The 1 pick above, plus these 24. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

  1. Codekev: Jev-like model built on Qwen2.5-0.5Bgithub.com · 2026-09-19
  2. ArticleQwen2.5-VL-32B: Smarter and Lighterqwenlm.github.io · 2025-03-24 · official
  3. ArticleQwen2.5-1M: Deploy your own Qwen with context length up to 1M tokensqwenlm.github.io · 2025-01-26 · official
  4. ArticleQwen2.5-Max: Exploring the intelligence of large-scale MoE modelqwenlm.github.io · 2025-01-28 · official
  5. ArticleQwen2.5-Coder-32B is an LLM that can code well that runs on my Macsimonwillison.net · 2024-11-13
  6. ArticleShow HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphscinegraphs.ai · 2026-02-08
  7. ArticleQwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1Msimonwillison.net · 2025-01-26
  8. ArticleQwen2.5-Coder Beats GPT-4o and Claude 3.5 Sonnet in Codingqwenlm.github.io · 2024-11-11 · official
  9. ArticleCivic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt dataitsmeduncan.com · 2026-04-25
  10. ArticleQwen2.5-VLqwenlm.github.io · 2025-01-27 · official
  11. CodeQwen2.5-Coder-32B with coding abilities matching those of GPT-4ogithub.com · 2024-11-09
  12. ArticleQwen2.5 Omni: See, Hear, Talk, Write, Do It Allqwenlm.github.io · 2025-03-26 · official
  13. ArticleAlibaba Qwen2.5-Omni-7B: Open Source End-to-End Multimodal AI Modelalizila.com · 2025-03-27
  14. ArticleQwen2.5-VL-32B: Smarter and Lightersimonwillison.net · 2025-03-25
  15. ArticleQwen2.5-Max: The Next Leap in AI Innovationmedium.com · 2025-01-29
  16. ArticleQwen2.5-Omni Technical Reporthuggingface.co · 2025-03-30
  17. PaperQwen2.5-Coder Technical Reportarxiv.org · 2024-11-11
  18. DiscussionQwen2.5-coder on the events occurring during the Tiananmen Square protestsnews.ycombinator.com · 2024-11-20
  19. CodeQwen2.5-VL: State-of-the-art multimodal LLMgithub.com · 2025-01-30
  20. DiscussionNew Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarkstwitter.com · 2025-01-28
  21. ArticleGuide how to use a local LLM Qwen2.5-coder-7B as an autocompelte in VSCodeeamag.me · 2024-10-29
  22. ArticleQwen2.5-Pluschat.qwenlm.ai · 2025-01-31
  23. ArticleShow HN: I made a free study tool powered by Qwen2.5freeflashcardgenerator.com · 2025-01-28 · 3 HN pts
  24. ArticleQwen2.5 Coderollama.com · 2024-11-11

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; 38 quantized builds for local use; a big base for builders (131 fine-tunes, adapters and merges).

  • As a service1Featherless
  • On own hardware38quantized builds
  • Built on13194 fine-tunes · 18 adapters · 19 merges
  • In apps23Hugging Face Spaces

Top Spaces running it: yasserrmd/MathMentor ♥ 1

Will it fit?

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

Fits a 16 GB card at INT4

About 0.9 GB at INT4, 1.9 GB at FP8, 3.7 GB at BF16: weights only, so leave room for the KV cache.

16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 0.9 GB of weights (estimate; KV cache and activations extra)INT40.9 GBFP8: about 1.9 GB of weights (estimate; KV cache and activations extra)FP81.9 GBBF16: about 3.7 GB of weights (estimate; KV cache and activations extra)BF163.7 GB
16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 0.9 GB of weights (estimate; KV cache and activations extra)INT40.9 GBFP8: about 1.9 GB of weights (estimate; KV cache and activations extra)FP81.9 GBBF16: about 3.7 GB of weights (estimate; KV cache and activations extra)BF163.7 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 16 repo commits so far

Teal is the weights (2024-09-16), amber triangles are 2 dated articles (each links to it), grey ticks are repo commits.

OctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2024-09-23: 1 repo commit2024-09-19: 1 repo commit2024-09-18: 9 repo commits2024-09-17: 3 repo commits2024-09-16: 2 repo commitsQwen2.5: A Party of Foundation Models · 2024-09-18Show HN: I made a free study tool powered by Qwen2.5 · 2025-01-28Weights 2024-09-16 · 2024-09-16Weights 2024-09-16now · 1 provider
OctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2024-09-23: 1 repo commit2024-09-19: 1 repo commit2024-09-18: 9 repo commits2024-09-17: 3 repo commits2024-09-16: 2 repo commitsQwen2.5: A Party of Foundation Models · 2024-09-18Show HN: I made a free study tool powered by Qwen2.5 · 2025-01-28Weights 2024-09-16 · 2024-09-16Weights 2024-09-16now · 1 provider

What people built on it

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

169 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.

38 quantized (Hugging Face model tree)94 fine-tunes (Hugging Face model tree)19 merges (Hugging Face model tree)18 adapters (Hugging Face model tree)38 quantized94 fine-tunes19 merges18 adapters
38 quantized (Hugging Face model tree)94 fine-tunes (Hugging Face model tree)19 merges (Hugging Face model tree)18 adapters (Hugging Face model tree)38 quantized94 fine-tunes19 merges18 adapters
GGUF bartowski/Qwen2.5-Math-1.5B-Instruct-GGUF for llama.cpp, Ollama, LM Studio 166.8k downloads MLX mlx-community/Qwen2.5-Math-1.5B-Instruct-4bit for Apple silicon 1.1k downloads

All variants →

Reference

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

What the card says

1 cited sentence

Summary generated, cited

Qwen2.5-Math-1.5B-Instruct is a 1.54B parameter instruction-tuned model designed for solving English and Chinese math problems.[1][2]

  1. parameters human
  2. “mainly supports solving English and Chinese math problems”

Generated 2026-10-07 15:09 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.

Use-case evidence

4 use cases

What it is good at 4 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: 1,543,714,304
Size bandS
MoEno
Context length4,096 (config.json max_position_embeddings)
Languagesen
PapersarXiv:2409.12122
LicenseApache 2.0 (apache-2.0)
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 Qwen2.5-Math-1.5B-Instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)3.7 GB · Edge (<4 GB)
FP8 (1 byte/param)1.9 GB · Edge (<4 GB)
INT4 (0.5 bytes/param)0.9 GB · Edge (<4 GB)

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

All variants

40 variants

Lineage

Fine-tuned from Qwen/Qwen2.5-Math-1.5B (same organization) Family: Qwen/Qwen2.5 169 derivatives on the Hub

Base model: Qwen/Qwen2.5-Math-1.5B

finetune: 94quantized: 38merge: 19adapter: 18

Top variants (40 shown, ranked by downloads)

Relation
Quant
40 rows
Variant Relation Quant Params Band License Author Likes Downloads
Skywork/Skywork-o1-Open-PRM-Qwen-2.5-1.5B finetune — — — other Skywork 34 267.5k
bartowski/Qwen2.5-Math-1.5B-Instruct-GGUF quantized GGUF — — apache-2.0 bartowski 3 166.8k
AI-MO/Kimina-Prover-Preview-Distill-1.5B finetune — 1.78B S apache-2.0 AI-MO 12 55.1k
unsloth/Qwen2.5-Math-1.5B-Instruct finetune — 1.54B S apache-2.0 unsloth 3 42.8k
unsloth/Qwen2.5-Math-1.5B-Instruct-bnb-4bit quantized -bnb 1.58B S apache-2.0 unsloth 2 27k
legraphista/Qwen2.5-Math-1.5B-Instruct-IMat-GGUF quantized GGUF — — apache-2.0 legraphista 0 26.5k
HuggingFaceH4/Qwen2.5-Math-1.5B-Instruct-PRM-0.2 finetune — 1.54B S — HuggingFaceH4 0 20.9k
mradermacher/Qwen2.5-Math-1.5B-Instruct-i1-GGUF quantized GGUF — — apache-2.0 mradermacher 0 14.6k
mradermacher/Qwen2.5-Math-1.5B-Instruct-GGUF quantized GGUF — — apache-2.0 mradermacher 0 8.7k
lmstudio-community/Qwen2.5-Math-1.5B-Instruct-GGUF quantized GGUF — — apache-2.0 lmstudio-community 1 7.4k
mergekit-community/Qwen3-1.5B-Instruct merge — 1.54B S — mergekit-community 6 6.8k
pthinc/prettybird_bce_basic_brain_mini quantized GGUF — — other pthinc 2 6.1k
second-state/Qwen2.5-Math-1.5B-Instruct-GGUF quantized GGUF — — apache-2.0 second-state 0 5.7k
tensorblock/Qwen2.5-Math-1.5B-Instruct-GGUF quantized GGUF — — apache-2.0 tensorblock 0 5.1k
gaianet/Qwen2.5-Math-1.5B-Instruct-GGUF quantized GGUF — — apache-2.0 gaianet 0 2.9k
DevQuasar-3/Qwen2.5-Math-1.5B-Instruct-GGUF quantized GGUF — — — DevQuasar-3 0 2.8k
jamescallander/Qwen2.5-Math-1.5B-Instruct_w8a8_g128_rk3588.rkllm finetune — — — apache-2.0 jamescallander 0 2.5k
featherless-ai-quants/Qwen-Qwen2.5-Math-1.5B-Instruct-GGUF quantized GGUF — — — featherless-ai-quants 0 1.9k
liodon-ai/Qwen2.5-Math-1.5B-Instruct-imatrix-GGUF quantized imatrix — — other liodon-ai 0 1.1k
mlx-community/Qwen2.5-Math-1.5B-Instruct-4bit quantized -4bit 1.54B S apache-2.0 mlx-community 0 1.1k
mlc-ai/Qwen2.5-Math-1.5B-Instruct-q4f16_1-MLC quantized — — — — mlc-ai 0 1.1k
tergel/qwen2.5-math-1.5b-instruct-gsm8k-fs-gpt4o-bon finetune — 1.54B S mit tergel 0 913
sheldonrobinson/Qwen2.5-Math-1.5B-Instruct-Q4_K_M-GGUF quantized GGUF — — apache-2.0 sheldonrobinson 0 810
mlc-ai/Qwen2.5-Math-1.5B-Instruct-q4f32_1-MLC quantized — — — — mlc-ai 0 552
rishiu/lucida-1.5b finetune — 1.54B S — rishiu 0 552
bunnycore/Qwen2.5-1.5B-Matrix merge — 1.78B S — bunnycore 2 407
sheldonrobinson/Qwen2.5-Math-1.5B-Instruct-Q8_0-GGUF quantized Q8_0 — — apache-2.0 sheldonrobinson 0 472
lipilipic/qwen2_5_math_1_5b_Instruct-NSFW-U-V2 finetune — 1.54B S apache-2.0 lipilipic 0 471
mergekit-community/SuperQwen-2.5-1.5B merge — 1.78B S — mergekit-community 2 360
Dat1710/nexus-1.5b finetune — 1.54B S apache-2.0 Dat1710 1 394
tuanpasg/puffin-linear-coder-math-Instruct merge — 1.78B S — tuanpasg 0 387
onnx-community/Qwen2.5-Math-1.5B-Instruct quantized — — — — onnx-community 0 382
Sakalti/SabaMath1.5-pro merge — 1.78B S apache-2.0 Sakalti 0 357
cutelemonlili/Qwen2.5-Math-1.5B-Instruct_MATH_training_response_Qwen2.5-7B-Instruct_common_correct_macro_7b finetune — 1.54B S other cutelemonlili 0 352
cutelemonlili/Qwen2.5-Math-1.5B-Instruct_MATH_training_response_AIDC-AI__Marco-o1_common_correct_macro_7b finetune — 1.54B S other cutelemonlili 0 343
itlwas/Qwen2.5-Math-1.5B-Instruct-Q4_K_M-GGUF quantized GGUF — — apache-2.0 itlwas 0 342
cutelemonlili/Qwen2.5-Math-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview finetune — 1.54B S other cutelemonlili 0 333
mukel/Qwen2.5-Math-1.5B-Instruct-GGUF quantized GGUF — — apache-2.0 mukel 0 328
Chamith2000/qwen2.5-math-mcq-lora adapter — — — — Chamith2000 0 301
matrixportalx/Qwen2.5-Math-1.5B-Instruct-GGUF quantized GGUF — — apache-2.0 matrixportalx 0 290

Repository changelog

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

Repository changelog 16 commits

DateCommitSHA
2024-09-23 Update README.md aafeb0f
2024-09-19 Upload ./tokenizer_config.json with huggingface_hub ed26cc9
2024-09-18 Update README.md 4997381
2024-09-18 Update README.md d655161
2024-09-18 Update README.md 9f97aed
2024-09-18 Update README.md 44d3e4d
2024-09-18 Update README.md 50280dd
2024-09-18 Create LICENSE 3e744fa
2024-09-18 Create README.md f903dd7
2024-09-18 Update generation_config.json 5177cd3
2024-09-18 Update generation_config.json e7ba350
2024-09-17 Update tokenizer_config.json 974197c
2024-09-17 Update generation_config.json 6e9d303
2024-09-17 Update generation_config.json c094ea1
2024-09-16 Upload folder using huggingface_hub 163f565
2024-09-16 initial commit 683500e

All providers

1 provider · 1 endpoint

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Qwen2.5-Math-1.5B-Instruct, 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/Qwen2.5-Math-1.5B-Instruct — — — — — — — live 2026-10-25

Articles and coverage

25 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.

Official1

Qwen2.5: A Party of Foundation Models
qwenlm.github.io2024-09-18officialauthorityHN front pageabout the Qwen2.5 familyHN 168 pts · 38 comments1,744 words
Qwen2.5 introduces dense decoder-only models pretrained on up to 18 trillion tokens, available in sizes from 0.5B to 72B parameters. Most variants are licensed under Apache 2.0, excluding the 3B and 72B models, and support a 128K context window with 8K generation limits. Specialized versions for coding and mathematics offer enhanced performance on benchmarks like HumanEval and MATH.written, reviewed, cited
  • Qwen2.5-Coder-7B-Instruct outperforms many larger language models across a range of programming languages and tasks.
  • Qwen2.5-Math-72B-Instruct general performance surpasses both Qwen2-Math-72B-Instruct and GPT4-o.

Analysis1

Show HN: I made a free study tool powered by Qwen2.5
freeflashcardgenerator.com2025-01-28about the Qwen2.5 familyHN 3 pts · 0 comments
All coverage tracked for this model (25) — append-only, nothing is ever removed
TitleSourcePublishedFirst seenSignals
kev: Jev-like model built on Qwen2.5-0.5Bgithub.com2026-09-192026-10-07hn
Civic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt dataitsmeduncan.com2026-04-252026-10-07hn
Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphscinegraphs.ai2026-02-082026-10-07hn
Qwen2.5-Omni Technical Reporthuggingface.co2025-03-302026-10-07hn
Alibaba Qwen2.5-Omni-7B: Open Source End-to-End Multimodal AI Modelalizila.com2025-03-272026-10-07hn
Qwen2.5 Omni: See, Hear, Talk, Write, Do It Allqwenlm.github.io official2025-03-262026-10-07hn
Qwen2.5-VL-32B: Smarter and Lightersimonwillison.net2025-03-252026-10-07hn
Qwen2.5-VL-32B: Smarter and Lighterqwenlm.github.io official2025-03-242026-10-07hn
Qwen2.5-Pluschat.qwenlm.ai2025-01-312026-10-07hn
Qwen2.5-VL: State-of-the-art multimodal LLMgithub.com2025-01-302026-10-07hn
Qwen2.5-Max: The Next Leap in AI Innovationmedium.com2025-01-292026-10-07hn
New Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarkstwitter.com2025-01-282026-10-07hn
Qwen2.5-Max: Exploring the intelligence of large-scale MoE modelqwenlm.github.io official2025-01-282026-10-07hn
Show HN: I made a free study tool powered by Qwen2.5freeflashcardgenerator.com2025-01-282026-10-07hn
Qwen2.5-VLqwenlm.github.io official2025-01-272026-10-07hn
Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1Msimonwillison.net2025-01-262026-10-07hn
Qwen2.5-1M: Deploy your own Qwen with context length up to 1M tokensqwenlm.github.io official2025-01-262026-10-07hn
Qwen2.5-coder on the events occurring during the Tiananmen Square protestsnews.ycombinator.com2024-11-202026-10-07hn
Qwen2.5-Coder-32B is an LLM that can code well that runs on my Macsimonwillison.net2024-11-132026-10-07hn
Qwen2.5-Coder Technical Reportarxiv.org2024-11-112026-10-07hn
Qwen2.5 Coderollama.com2024-11-112026-10-07hn
Qwen2.5-Coder Beats GPT-4o and Claude 3.5 Sonnet in Codingqwenlm.github.io official2024-11-112026-10-07hn
Qwen2.5-Coder-32B with coding abilities matching those of GPT-4ogithub.com2024-11-092026-10-07hn
Guide how to use a local LLM Qwen2.5-coder-7B as an autocompelte in VSCodeeamag.me2024-10-292026-10-07hn
Qwen2.5: A Party of Foundation Modelsqwenlm.github.io official2024-09-182026-10-07hn

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

  • Qwen2-1.5B-Instruct · 1.54B
    same size band (S), same task (text-generation), permissive license
  • Qwen2-1.5B · 1.54B
    same size band (S), same task (text-generation), permissive license
  • ReaderLM-v2 · 1.54B
    same size band (S), same task (text-generation)

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:39 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:09 UTC · Last verified 2026-10-25

Follow Qwen2.5-Math-1.5B-Instruct

Watch this model

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