Skip to content

Best GPU for DeepSeek-R1-Distill-32B Locally

Real-time prices and hardware recommendations updated for August 2026.

32B
32B
dense

DeepSeek-R1-Distill-32B is a dense model: all 32B parameters activate on every token, so generation speed is bound by how fast your card can stream the full weights.

To run DeepSeek-R1-Distill-32B locally you need roughly 22.5 GB of VRAM at Q4_K_M quantization with a 32k token context. The best-value card that fits is the GeForce RTX 3090 (24 GB), which should generate around 10 tokens per second.

Adjust Context Length

Slide to popular sizes or type any value manually.

k tokens
8k
16k
32k
64k
128k
256k
Budget EntryQ3_K_M quant
13.8 GB
4.1 GB
Total VRAM:17.9 GB

Recommended Hardware

GeForce RTX 3090
311 tok/sprefill
12 tok/sgeneration
CAD 2199.99·24GB VRAM
View Card
RTX PRO 4000 Blackwell
316 tok/sprefill
14 tok/sgeneration
CAD 4632.44·24GB VRAM
View Card
GeForce RTX 4090
423 tok/sprefill
17 tok/sgeneration
CAD 6137.99·24GB VRAM
View Card

Q3 weights (~14GB) plus 32k GQA KV cache push past 16GB. 24GB cards are the practical entry point for this 32B model.

Balanced Sweet SpotQ4_K_M quant
18.4 GB
4.1 GB
Total VRAM:22.5 GB

Recommended Hardware

GeForce RTX 3090
311 tok/sprefill
10 tok/sgeneration
CAD 2199.99·24GB VRAM
View Card
GeForce RTX 4090
423 tok/sprefill
14 tok/sgeneration
CAD 6137.99·24GB VRAM
View Card

Runs comfortably on 24GB cards at Q4. Strong reasoning performance unconstrained by VRAM.

Near LosslessQ8_0 quant
36.8 GB
4.1 GB
Total VRAM:40.9 GB

Recommended Hardware

RTX PRO 5000 Blackwell
496 tok/sprefill
13 tok/sgeneration
CAD 11190.7·48GB VRAM
View Card
RTX A6000
184 tok/sprefill
5 tok/sgeneration
CAD 11399·48GB VRAM
View Card

Full precision requires workstation-grade 48GB+ cards for the weight matrix alone.

Other models with the same VRAM requirement

Because DeepSeek-R1-Distill-32B's weights fit a 24 GB card, other models of a similar size run on the same GPU. Generation speed varies — mixture-of-experts models are faster, dense models slower — but any of these load in the same VRAM:

OpenReasoning-Nemotron-32B32B · Qwen2.5-32BQwen2.5-32B32.5BQwen2.5-Coder-32B32.5BQwQ-32B32.5BQwen3-32B32.8BGemma 4 31B31B

Optimizing Setup for DeepSeek-R1-Distill-32B

Quantization Recommendations

For daily coding and reasoning tasks, Q4_K_M (4-bit quantization) offers the best balance of quality and memory efficiency — it reduces memory requirements by over 70% with minimal quality loss compared to FP16. Q8 and higher presets preserve more fidelity at the cost of significantly higher VRAM usage, which may force layer offloading and hurt throughput.

Recommended Local Software

We recommend using Ollama as the primary runner for local inference due to its automated GPU model splitting and context cache optimizations. For advanced fine-tuning or quantization splits, llama.cpp with Flash Attention compiled natively provides the best granular control.

Running DeepSeek-R1-Distill-32B locally — FAQ

How much VRAM do I need to run DeepSeek-R1-Distill-32B?

At a 32k context with KV cache quantization on, DeepSeek-R1-Distill-32B needs about 22.5 GB of VRAM at Q4_K_M — the quantization most people should use. Dropping to Q3_K_M brings that down to roughly 17.9 GB at some quality cost, while Q8_0 needs about 40.9 GB for the best quality this model can give.

What size graphics card does DeepSeek-R1-Distill-32B fit on?

DeepSeek-R1-Distill-32B needs about 22.5 GB at Q4_K_M, so a 24 GB card is the smallest common size that holds it entirely in VRAM. Anything smaller has to offload layers to system RAM, which typically costs you most of your generation speed.

Which quantization should I use for DeepSeek-R1-Distill-32B?

Use Q4_K_M unless you have VRAM to spare. It needs about 22.5 GB and loses very little quality against full precision. Q8_0 needs about 40.9 GB for a quality gain most people cannot detect in everyday coding and chat. Spend spare VRAM on a longer context instead.

How does context length affect the VRAM DeepSeek-R1-Distill-32B needs?

Model weights are fixed, but the KV cache grows linearly with context. For DeepSeek-R1-Distill-32B at a 32k context the cache is about 4.1 GB; doubling to 64k takes it to roughly 8.2 GB. Turning KV cache quantization off doubles those figures again.

Can the same GPU run other models similar to DeepSeek-R1-Distill-32B?

Yes. DeepSeek-R1-Distill-32B needs about 22.5 GB at Q4_K_M, and any model whose weights fit the same card runs on it — including OpenReasoning-Nemotron-32B (32B, based on Qwen2.5-32B), Qwen2.5-32B (32.5B), Qwen2.5-Coder-32B (32.5B), QwQ-32B (32.5B), Qwen3-32B (32.8B), Gemma 4 31B (31B). The weights fit the same GPU; generation speed varies (mixture-of-experts models are faster, dense models slower).

How token speeds are estimated

Two metrics are shown per GPU: Read tok/s (how fast the model ingests your prompt) and Decode tok/s (how fast it streams tokens back). They model fundamentally different bottlenecks.

📖

Read (Prefill)

The prompt is processed in one parallel pass. This is compute-bound: it saturates the GPU's tensor cores.

read tok/s ≈ TFLOPS × readFactor × 400 ÷ activeParams

Decode (Generation)

Each new token requires loading the entire model's active weights from VRAM. This is memory-bandwidth-bound: the GPU stalls waiting for data, not computing.

decode tok/s ≈ bandwidth × decodeFactor ÷ (weights + kv_cache)

Weights = (activeParams × bits ÷ 8) × 1.15 overhead. KV cache per step = activeParams × multiplier × contextK.

Architecture utilization factors

Architecture
Decode
Read
Blackwell, Xe2
0.45
0.55
Ada Lovelace, RDNA 4, Battlemage
0.38
0.48
Ampere, Turing, RDNA 3, Xe-HPG
0.28
0.38
Volta, RDNA 1/2
0.2
0.25
Pre-tensor-core (Pascal, Maxwell, Kepler, GCN, Alchemist)
0.12
0.15

Left: decode factor — Right: read factor

Data sources

TFLOPS and memory bandwidth are read from the GPU database. When missing, bandwidth falls back to a hardcoded dictionary.

Limitations

These are analytical estimates, not benchmark results. Use them as a relative comparison, not an absolute performance guarantee.