llmrun
DeepSeekDeepSeek R1Qwen2ForCausalLM

DeepSeek R1 Distill Qwen 32B — Hardware Requirements & GPU Compatibility

ChatReasoningFunctions

DeepSeek R1 Distill Qwen 32B takes the reasoning capabilities developed in the full 684.5B R1 model and distills them into the 32.8 billion parameter Qwen 2.5 architecture. The result is a dense model that punches well above its weight class on math, science, and coding reasoning tasks, often matching models two to three times its size. At around 32.8 billion parameters, this model fits comfortably on a single high-end consumer GPU when quantized to 4-bit precision, making it one of the most capable reasoning models you can run on a desktop workstation.

32.8B params · dense131K contextMIT350.1K downloads1.7K likes163.2K quant downloads
A

Runs well on a 24 GB GPU

Runs from16 GB IQ2_M · 16KBest on24 GB Q4_K_M · ~32 tok/s · 8KMacs from18 GB IQ2_XS · ~10 tok/s

Score 97.2#67 of 106 open#14 of 36 that fit 24 GBMIT

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

llmrun Composite Score →

97.2

Benchmarks · tier chart ↓
Among 106 open modelsHow the Composite Score is built

Run DeepSeek R1 Distill Qwen 32B

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

Ollama
one command · needs Ollama installed
$ollama run deepseek-r1:32b

Q4_K_M · needs ~24.3 GB · 16K context

Download: DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf19.85 GBbartowski

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 32 GB GPU

  • The easiest way to try this model
  • Running in a few minutes, easy setup
  • Chat right here or connect any app

$5+ bonus for new users

How Much VRAM Does DeepSeek R1 Distill Qwen 32B Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
14.8 GB22.8 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~44 tok/s
15.2 GB23.2 GB3-bit small — 3-bit small quantizationFits: 32K context · ~43 tok/s
16.8 GB24.9 GB3-bit medium — 3-bit medium quantizationFits: 16K context · ~39 tok/s
17.2 GB25.3 GB4-bit · legacy — 4-bit legacy quantizationFits: 16K context · ~38 tok/s
20.5 GB28.6 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 8K context · ~32 tok/s
24.2 GB32.2 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffDoes not fit: needs 27.9 GB
27.9 GB35.9 GB6-bit, very good — 6-bit quantization, very good qualityDoes not fit: needs 31.6 GB
33.6 GB41.7 GB8-bit, near-lossless — 8-bit quantization, near-losslessDoes not fit: needs 37.4 GB

Selected Q4_K_M

4-bit medium quantization

24.3GBat 16K context

Weights
19.7 GB
KV cache
4.3 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · fits up to 8K context · ~32 tok/s

≥50 tok/s needs ≥1.57 TB/s · RTX 5090 ~57

Which Hardware Can Run DeepSeek R1 Distill Qwen 32B?

Q4_K_M · 20.5 GB

DeepSeek R1 Distill Qwen 32B (Q4_K_M) requires 20.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 27+ GB is recommended. Using the full 131K context window can add up to 33.8 GB, bringing total usage to 54.3 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run DeepSeek R1 Distill Qwen 32B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8–12 GB · RTX 4060, RTX 3060 12GBDoesn't fit — smallest quant needs 13.6 GB8 GB tier →12 GB tier →
16 GB · RTX 5060 Ti 16GBIQ2_M · 15.7 GB · ~25 tok/s · 16K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 24.3 GB · ~32 tok/s · 8Ktight24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 24.3 GB · ~4 tok/s · 16KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 24.3 GB · ~19 tok/s · 128KMacs →

How good is DeepSeek R1 Distill Qwen 32B?

The llmrun Score merges 3 public benchmark boards into a single figure, where 100 represents the average for open models.

Score vs VRAM in the 24 GB tier

  • DeepSeek R1 Distill Qwen 32B
  • Other models
  • Best Score for its VRAM

#14 of 36 that fit 24 GB

Each dot is a model at the best quant that fits a 24 GB GPU. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.

Full 24 GB ranking →

Benchmarks

Here are all 3 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.

  • GPQA Diamond

    Epoch AI · Jan 2025Independent

    64.1%

    #41/100 open

    Independent
  • AIME 2024/2025

    Epoch AI · Jan 2025Independent

    55.6%

    #44/88 open

    Independent
  • BALROG

    Epoch AI · Jan 2025Independent

    19.5%

    #5/15 open

    Independent
All 3 DeepSeek R1 Distill Qwen 32B benchmarks

In the 24 GB class

36 models fit 24 GB

Same Score, only models that fit 24 GB at their best quant: the ranking a 24 GB owner actually chooses from.

  1. #1

    Qwen3.8 27BAlibaba

    122.0

    ~38 tok/s · 17.9 GB

  2. #2

    Qwen3.6 27BAlibaba

    111.2

    ~38 tok/s · 17.9 GB

  3. #3

    Qwen3.6 35B A3BAlibaba

    106.8

    ~151 tok/s · 22.0 GB

  4. #4

    Gemma 4 31B ITGoogle

    106.7

    ~32 tok/s · 21.7 GB

  5. #5

    Gemma 4 26B A4B ITGoogle

    105.8

    ~171 tok/s · 16.5 GB

  6. #6

    Qwen3.5 35B A3BAlibaba

    105.8

    ~151 tok/s · 22.0 GB

Full 24 GB ranking →RTX 4090 page →

Alternatives to DeepSeek R1 Distill Qwen 32B

DeepSeek R1 family · 13 models →

Official models with an llmrun Score, each answering one question; numbers are at the best quant that fits a 24 GB GPU.

Similar models

10
ModelScoreVRAMtok/sWhy it is similar
Gemma 4 31B ITGoogle106.721.7 GB~32similar score
Gemma 4 26B A4B ITGoogle105.816.5 GB~171similar score
Qwen3.5 35B A3BAlibaba105.822 GB~151similar score
Qwen3.5 27BAlibaba103.817.9 GB~38similar score
Seed OSS 36B InstructByteDance-Seed102.522.8 GB~31similar score
Qwen3 30B A3B Thinking 2507Alibaba100.719.4 GB~173similar score
Qwen3.5 9BAlibaba99.46.6 GB~103similar score
Qwen3.5 4BAlibaba98.53.4 GB~201similar score
Qwen3 14BAlibaba98.011.9 GB~69similar score
Qwen3 8BAlibaba93.97.6 GB~119similar score
Fine-tunes & variants(3)

Specifications

Publisher
DeepSeek
Family
DeepSeek R1
Parameters
32.8B
Architecture
Qwen2ForCausalLM
Context Length
131,072 tokens
Vocabulary Size
152,064
Release Date
2025-01-20
License
MIT

Resources

Frequently Asked Questions

How much VRAM does DeepSeek R1 Distill Qwen 32B need?

DeepSeek R1 Distill Qwen 32B requires 20.5 GB of VRAM at Q4_K_M, or 66.4 GB at BF16. Full 131K context adds up to 33.8 GB (54.3 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 32.8B × 4.8 bits ÷ 8 = 19.7 GB

KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 34.6 GB (at full 131K context)

VRAM usage by quantization

20.5 GB
54.3 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run DeepSeek R1 Distill Qwen 32B?

Yes, at Q5_K_S (23.4 GB) or lower. Higher quantizations like Q5_K_M (24.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for DeepSeek R1 Distill Qwen 32B?

For DeepSeek R1 Distill Qwen 32B, Q4_K_M (20.5 GB) offers the best balance of quality and VRAM usage. Q4_K_L (20.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 9.8 GB.

VRAM requirement by quantization

IQ2_XXS
9.8 GB
IQ3_S
14.8 GB
Q3_K_L
17.6 GB
Q4_K_M ★
20.5 GB
Q5_0
21.3 GB
BF16
66.4 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run DeepSeek R1 Distill Qwen 32B on a Mac?

Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run DeepSeek R1 Distill Qwen 32B, the smallest at IQ2_XS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 20.5 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).

Can I run DeepSeek R1 Distill Qwen 32B locally?

Yes — DeepSeek R1 Distill Qwen 32B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is DeepSeek R1 Distill Qwen 32B?

At Q4_K_M, DeepSeek R1 Distill Qwen 32B can reach ~234 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~32 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 20.5 × 0.65 = ~254 tok/s

Estimated speed at Q4_K_M (20.5 GB)

~254 tok/s
~32 tok/s
~254 tok/s
~234 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of DeepSeek R1 Distill Qwen 32B?

At Q4_K_M, the download is about 19.66 GB. The full-precision BF16 version is 65.53 GB. The smallest option (IQ2_XXS) is 9.01 GB.

Which GPUs can run DeepSeek R1 Distill Qwen 32B?

7 consumer GPUs can run DeepSeek R1 Distill Qwen 32B at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU has plenty of headroom for comfortable inference.

Which devices can run DeepSeek R1 Distill Qwen 32B?

122 devices with unified memory can run DeepSeek R1 Distill Qwen 32B at Q4_K_M (20.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.