DeepSeek-R1-Distill-Qwen-7B

7B

DeepSeek

R1 reasoning in a 7B footprint. Best value for 8–12GB VRAM CoT experiments.

⬇ 76.0K HF downloads♥ 141 likesbartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF· stats from 8/8/2026
Consumer GPUMac / Apple SiliconCPU / VPS

131K

Max Context

2

Quant Variants

EXL2 4.65bpw

Best Quality

97.8%

Accuracy Retained

Calculate VRAMHugging FaceCompare

Quantization Variants

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

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

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M4.855.4 GB3.0%152 tok/sEstimated
CalcHF
EXL24.65bpw4.655.2 GB2.2%210 tok/sEstimated
CalcHF

Similar models

Compare with DeepSeek-R1-Distill-Llama-8B
8B

DeepSeek-R1-Distill-Llama-8B

DeepSeek

Consumer GPUMac / Apple Silicon
4.9 GBmin VRAM·98.8%accuracy

R1 reasoning distilled into Llama 3.1 8B. Best chain-of-thought for 8–12GB cards; huge community GGUF support.

16B

DeepSeek-V2-Lite Chat

DeepSeek

Consumer GPUMac / Apple Silicon
9.6 GBmin VRAM·97.0%accuracy

MoE general model (~2.4B active). Long context and strong multilingual chat.

14B

DeepSeek-R1-Distill-Qwen-14B

DeepSeek

Consumer GPU
9.2 GBmin VRAM·98.0%accuracy

R1 reasoning distilled into 14B. Huge community interest; excellent chain-of-thought.

32B

DeepSeek-R1-Distill-Qwen-32B

DeepSeek

Consumer GPUPro GPU
16.8 GBmin VRAM·97.4%accuracy

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