DeepSeek-R1-Distill-Qwen-32B

DeepSeek32.5B paramsMIT License128K contextReleased 2025-01-20

The practical way most people actually run "DeepSeek-R1" at home: a 32B dense model distilled from R1's reasoning traces onto a Qwen2.5 base, sized to fit a single 24 GB GPU.

Last verified 2026-07 · Page created; Q4_K_M/Q5_K_M/Q8_0/FP16(BF16) sizes verified against bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF.

What it is good at

This is a Qwen2.5-32B base fine-tuned on reasoning traces generated by full DeepSeek-R1, which is what lets a 32B dense model punch well above its parameter count on math, code, and multi-step logic — it inherits R1's "think before answering" style without needing R1's 671B footprint. It is MIT-licensed with no restriction on commercial use.

Being dense rather than MoE, every one of its 32.5B parameters activates per token, so throughput and VRAM scale exactly the way they do for any other 32B-class model — no expert-routing surprises to account for.

The hardware it wants

Q4_K_M is 19.85 GB, which comfortably fits a single 24 GB GPU (RTX 3090/4090) with real headroom for context and a chat session. Q5_K_M (23.26 GB) is a tighter fit on 24 GB once you account for KV cache — workable at shorter context, tight at the full window. Q8_0 (34.82 GB) needs a 48 GB card or two pooled 24 GB cards.

Because reasoning models "think out loud" before answering, effective context use runs higher than a normal chat model at the same nominal context length — budget more headroom than you would for a straight-answer 32B when picking a quant.

VRAM by quantization

QuantFile sizeVRAM @ 8K ctxVRAM @ 32K ctx8 GB16 GB24 GB32 GB48 GB
FP1665.5 GB80.0 GB94.1 GBDoesn't fitDoesn't fitDoesn't fitDoesn't fitDoesn't fit
Q8_034.8 GB44.7 GB58.7 GBDoesn't fitDoesn't fitDoesn't fitDoesn't fitFits comfortably
Q5_K_M23.3 GB31.4 GB45.4 GBDoesn't fitDoesn't fitDoesn't fitFits comfortablyFits comfortably
Q4_K_M19.9 GB27.5 GB41.5 GBDoesn't fitDoesn't fitTight — reduced contextFits comfortablyFits comfortably

Fit verdicts use the 8K context preset. Estimated from published weight sizes plus standard KV-cache math — see methodology.

Runs on

RTX 4090 (24 GB)
best fit Q4_K_MTight — reduced context
RX 7900 XTX (24 GB)
best fit Q4_K_MTight — reduced context
RTX 5090 (32 GB)
best fit Q5_K_MFits comfortably
RTX 6000 Ada (48 GB)
best fit Q8_0Fits comfortably

Unified-memory machines — Apple Silicon Mac Studio/MacBook Pro (Max/Ultra chips) and AMD Strix Halo mini-PCs — share system RAM and GPU memory in one pool, so a 64–128 GB configuration can hold models that would otherwise need multiple discrete GPUs. Throughput is bandwidth-bound like any GPU; it isn’t modeled in the table above yet.

Recommended builds

Three ways to size a machine for DeepSeek-R1-Distill-Qwen-32B, from the smallest GPU that fits to the no-compromise option with headroom for the next model up.

BudgetSmallest GPU that fits at Q4 — runs it, no headroom for bigger contexts.
BalancedOne tier up — comfortable context length, room to run alongside other apps.
No-compromiseFits at Q8 or FP16, or leaves room to step up to the next model class.

Tokens/sec expectations

GPUBandwidthEst. tok/s (Q4_K_M)
RTX 50901792 GB/s~63.2
RTX 40901008 GB/s~35.5
RTX 6000 Ada960 GB/s~33.9
RX 7900 XTX960 GB/s~33.9
RTX 5080960 GB/s~33.9
RTX 5070 Ti896 GB/s~31.6

Estimated from memory bandwidth ÷ active weight size — a ceiling, not a measured figure. Real throughput depends on the inference engine, batch size, and context length.

Build it, or rent the compute?

Owning the hardware is a one-time cost that keeps paying off the more you actually use it — every run after the first is free, the data never leaves your machine, and the GPU still does everything else a PC does (gaming, editing, the rest of your workload) between AI sessions. Renting cloud GPU time trades that upfront cost for pay-as-you-go pricing with no idle hardware to maintain, which wins for occasional, bursty, or much-larger-than-consumer-VRAM jobs. For a model that fits comfortably in the VRAM tiers above and gets used regularly, owning the GPU tends to be the cheaper path over time — for anything larger than a single card can hold, renting is often the more practical starting point.

Frequently asked questions

Does this fit in 24 GB?

Yes at Q4_K_M (19.85 GB weights) with room to spare for context. Q5_K_M (23.26 GB) is workable on 24 GB but tight once the reasoning chain and KV cache are accounted for — Q4_K_M is the safer default on a single 24 GB card.

Is this actually DeepSeek-R1, just compressed?

No — it is a separate, much smaller Qwen2.5-32B model fine-tuned on R1's reasoning outputs, not a quantized version of the 671B model. It carries a lot of R1's reasoning behavior but is not identical to running full R1.

What GPU should I buy for this specifically?

A single 24 GB card (RTX 3090 used, or RTX 4090/5070 Ti new) covers Q4_K_M and Q5_K_M with room for a real chat session. If you want Q8_0 headroom too, size up to 32-48 GB.

Related models:Qwen3 32B