DeepSeek-R1-Distill-Qwen-32B

32B

DeepSeek

R1 distilled to 32B. Near-frontier reasoning on a single 24GB card (Q3/Q4).

49.7K HF downloads325 likesbartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF· stats from 9/21/2026
Consumer GPUPro GPU

131K

Max Context

3

Quant Variants

GGUF Q4_K_M

Best Quality

97.4%

Accuracy Retained

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = site benchmarks · Estimated = formula · Community = public reports

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ3_K_M3.8717.8 GB7.2%50 tok/sEstimated
CalcHF
GGUFQ4_K_M4.8522.2 GB2.6%42 tok/sEstimated
CalcHF
EXL23.5bpw3.516.8 GB4.5%65 tok/sEstimated
CalcHF

Running DeepSeek-R1-Distill-Qwen-32B locally

At Q4_K_M and 4K of context, DeepSeek-R1-Distill-Qwen-32B needs about 21.7 GB — 18.7 GB of weights, 1.00 GB of KV cache and a 2.0 GB activation buffer. The smallest card in this index that clears that comfortably is the RTX 5090 at 32 GB, and 24 of the 63 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 7.00 GB, taking the total to 29.4 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 128K; holding all of it at Q4_K_M would need about 56 GB.

Which build to download

This index tracks 2 formats for it — GGUF, EXL2 — across 3 levels. Q4_K_M carries the lowest published perplexity loss at 2.6%. The fastest level measured here is EXL2 3.5bpw at 65 tok/s on an RTX 4090, batch 1. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 and CUDA only.

Common questions

How much VRAM does DeepSeek-R1-Distill-Qwen-32B need?
About 21.7 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 29.4 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
Will DeepSeek-R1-Distill-Qwen-32B run on a 32GB GPU?
Yes — at Q4_K_M and 4K context it needs about 21.7 GB, which leaves 10.3 GB spare on a RTX 5090. That is the smallest card in this index that clears it comfortably; 24 of 63 do.
Which quantization of DeepSeek-R1-Distill-Qwen-32B should I use?
Q4_K_M has the lowest published quality loss (2.6%), and Q4_K_M is the level most people run. All 3 levels in the index are Q3_K_M, Q4_K_M, EXL2 3.5bpw.

Where this model fits

Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.

Ships in
GGUFEXL2
Compared here
GGUF vs EXL2

This page's figures change when the model or the runtime does.Last updated 2026-09-21 RSS → /feed.xml