- Size
- 32.8B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, MIT LicenseOur reading, check the licence: You can use, change and redistribute the model for any purpose, including commercially. Keep the copyright notice and the licence text with copies. You do not have to share your changes.
- On the Hub since
- 20 Jan 2025the date the repo was created
- Context length
- 128k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Qwen2ForCausalLM
- On Hugging Face
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B368k downloads in the last 30 days, 1.7k likes
Scores
- default setting64.1%±2.828 Aug 2026, log
Epoch's name: DeepSeek-R1-Distill-Qwen-32B. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- default setting55.6%±6.228 Aug 2026, log
Epoch's name: DeepSeek-R1-Distill-Qwen-32B. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- default setting19.5%±1.626 Jan 2025, balrogai.com
Epoch's name: DeepSeek-R1-Distill-Qwen-32B. Best closed model on this set: gpt-6-astra_max, 68.3% (OpenAI). All 41 results
- default setting45.6%LiveBench Leaderboard
Epoch's name: DeepSeek-R1-Distill-Qwen-32B. Best closed model on this set: gemini-2.5-pro-exp-03-25, 82.3% (Google DeepMind). All 54 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 2.0 GB, worked out from the model's config (deepseek-ai/DeepSeek-R1-Distill-Qwen-32B), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF (converted by bartowski), 70k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XS | 12.8 GBfile size | 15.3 GB12.8 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:IQ3_XSOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:IQ3_XSDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-IQ3_XS.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q3_K_S | 13.4 GBfile size | 15.9 GB13.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q3_K_SOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q3_K_SDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q3_K_S.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| IQ3_M | 13.8 GBfile size | 16.3 GB13.8 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:IQ3_MOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:IQ3_MDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-IQ3_M.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q3_K_M | 14.8 GBfile size | 17.3 GB14.8 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q3_K_MOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q3_K_MDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q3_K_M.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q3_K_L | 16.1 GBfile size | 18.6 GB16.1 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q3_K_LOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q3_K_LDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q3_K_L.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| IQ4_XS | 16.5 GBfile size | 19.0 GB16.5 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:IQ4_XSOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:IQ4_XSDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-IQ4_XS.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q3_K_XL | 16.7 GBfile size | 19.2 GB16.7 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q3_K_XLOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q3_K_XLDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q3_K_XL.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| IQ4_NL | 17.4 GBfile size | 19.9 GB17.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:IQ4_NLOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:IQ4_NLDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-IQ4_NL.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q4_0 | 17.4 GBfile size | 19.9 GB17.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_0Ollama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_0Download hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q4_0.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q4_K_S | 17.5 GBfile size | 20.0 GB17.5 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_SOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_SDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q4_K_S.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q4_K_M | 18.5 GBfile size | 21.0 GB18.5 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_MOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_MDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q4_K_L | 19.0 GBfile size | 21.5 GB19.0 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_LOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_LDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q4_K_L.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q4_1 | 19.2 GBfile size | 21.7 GB19.2 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_1Ollama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_1Download hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q4_1.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q5_K_S | 21.1 GBfile size | 23.6 GB21.1 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q5_K_SOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q5_K_SDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q5_K_S.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q5_K_M | 21.7 GBfile size | 24.2 GB21.7 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q5_K_MOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q5_K_MDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q5_K_L | 22.1 GBfile size | 24.6 GB22.1 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q5_K_LOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q5_K_LDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q5_K_L.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q6_K | 25.0 GBfile size | 27.5 GB25.0 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q6_KOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q6_KDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q6_K.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q6_K_L | 25.4 GBfile size | 27.9 GB25.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q6_K_LOllama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q6_K_LDownload hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q6_K_L.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| Q8_0 | 32.4 GBfile size | 34.9 GB32.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q8_0Ollama ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q8_0Download hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q8_0.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
| BF16 | 61.0 GBfile size, 2 parts | 63.5 GB61.0 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:BF16Download hf download bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-bf16/DeepSeek-R1-Distill-Qwen-32B-bf16-*-of-00002.gguf" --local-dir DeepSeek-R1-Distill-Qwen-32B-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitmlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit | 17.2 GBfile size | 19.7 GB17.2 + 2.0 + 0.50 | Download page |
| MLX 8bitmlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX-8Bit | 32.4 GBfile size | 34.9 GB32.4 + 2.0 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 61.0 GBfile size | 63.5 GB61.0 + 2.0 + 0.50 |
hf download deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --local-dir DeepSeek-R1-Distill-Qwen-32BOther conversions (19; sizes not read)
- RedHatAI/DeepSeek-R1-Distill-Qwen-32B-quantized.w4a16 Other, w4a16, 3.2k downloads
- RedHatAI/DeepSeek-R1-Distill-Qwen-32B-FP8-dynamic FP8, 3.1k downloads
- unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit bitsandbytes, 4bit, 1.6k downloads
- empirischtech/DeepSeek-R1-Distill-Qwen-32B-gptq-4bit GPTQ, 4bit, 1.1k downloads
- Valdemardi/DeepSeek-R1-Distill-Qwen-32B-AWQ AWQ, 818 downloads
- inarikami/DeepSeek-R1-Distill-Qwen-32B-AWQ AWQ, 710 downloads
- unsloth/DeepSeek-R1-Distill-Qwen-32B-unsloth-bnb-4bit bitsandbytes, 4bit, 320 downloads
- jkim96/DeepSeek-R1-Distill-Qwen-32B-DASHQ-INT3-g128 Other, 147 downloads
- nm-testing/DeepSeek-R1-Distill-Qwen-32B-NVFP4 NVFP4, 134 downloads
- jkim96/DeepSeek-R1-Distill-Qwen-32B-DASHQ-INT2-g32 Other, 118 downloads
- RedHatAI/DeepSeek-R1-Distill-Qwen-32B-quantized.w8a8 Other, w8a8, 93 downloads
- avoroshilov/DeepSeek-R1-Distill-Qwen-32B-GPTQ_4bit-128g GPTQ, 4bit, 41 downloads
- drawais/DeepSeek-R1-Distill-Qwen-32B-AWQ-INT4 AWQ, int4, 35 downloads
- JamAndTeaStudios/DeepSeek-R1-Distill-Qwen-32B-FP8-Dynamic FP8, 33 downloads
- chriswritescode/DeepSeek-R1-Distill-Qwen-32B-FP8-Dynamic FP8, 22 downloads
- cortecs/DeepSeek-R1-Distill-Qwen-32B-FP8-Dynamic FP8, 20 downloads
- graelo/DeepSeek-R1-Distill-Qwen-32B-AWQ AWQ, 20 downloads
- frankdarkluo/DeepSeek-R1-Distill-Qwen-32B-GPTQ-Int8 GPTQ, int8, 18 downloads
- OPEA/DeepSeek-R1-Distill-Qwen-32B-int4-gptq-sym-inc GPTQ, int4, 16 downloads
The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- stepfun-ai/StepFun-Prover-Preview-32B32.8B2.0kUnreviewed
- stepfun-ai/StepFun-Formalizer-32B32.8B356Unreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.