DeepSeek R1 Distill 7B

At the default Q4_K_M, 105 of 140 phones have enough estimated usable memory; 91 also reach 3+ tokens/s. On Mac, 54 of 54 exact configurations pass using that quant or a smaller tracked fallback.

Params
7.6B
Family
deepseek
Released
2025-01
Tags
reasoning

Downloads & memory by quant

The download is only the weights — add KV cache and runtime to get what your phone actually needs. “Memory-fit” only means it can load; “usable” also requires an estimated 3+ tokens/s. Each row uses that row's quant. ★ = recommended.

QuantDownloadMemory neededPhone reality
Q2_K3 GB~4.3 GB137 memory-fit · 125 usable
Q3_K_M3.8 GB~5.1 GB137 memory-fit · 125 usable
IQ4_XS4.2 GB~5.5 GB130 memory-fit · 97 usable
Q4_04.4 GB~5.8 GB130 memory-fit · 97 usable
Q4_K_S4.5 GB~5.9 GB130 memory-fit · 97 usable
Q4_K_M4.7 GB~6.1 GB105 memory-fit · 91 usable
Q5_K_M5.4 GB~6.8 GB105 memory-fit · 89 usable
Q6_K6.3 GB~7.7 GB105 memory-fit · 89 usable
Q8_08.1 GB~9.6 GB59 memory-fit · 59 usable

DeepSeek R1 Distill 7B at Q4_K_M on 140 phones

This table is fixed to the recommended Q4_K_M, on each phone's largest RAM option. Counts for smaller quants above will differ. All phones are shown, sorted by fit and estimated experience; tap one for the full report.

PhoneChip · RAMNeedsSpeedVerdict

~ = bandwidth-based estimate · ✓ = measured on real hardware

DeepSeek R1 Distill 7B on 54 Mac configurations

Each Mac uses the recommended Q4_K_M at 4K context when it fits, or the largest smaller tracked quant that fits. Each row links to the full report with a macOS-specific setup guide.

MacUnified memoryQuantWorking budgetNeedsEstimated speedVerdict

FAQ

How much RAM do I need to run DeepSeek R1 Distill 7B on a phone?

At Q4_K_M, DeepSeek R1 Distill 7B needs ~6.1GB of usable memory (weights + KV cache + runtime). In practice that means a 12GB+ Android phone or a 12GB+ iPhone — iOS lets a single app use less of its RAM than Android does.

How fast does DeepSeek R1 Distill 7B run on a flagship phone?

On the OPPO Find X8 Pro (Dimensity 9400) it runs at ~8.2 tokens/s at Q4_K_M, estimated from memory bandwidth. Anything above ~8 tokens/s feels smooth for chat.

Can an iPhone run DeepSeek R1 Distill 7B?

Yes — the iPhone Air runs it at ~7.4 tokens/s at Q4_K_M, using 6.1GB of its ~7.8GB usable memory.

What is the best quantization of DeepSeek R1 Distill 7B for mobile?

Q4_K_M (4.7GB download) is the size/quality sweet spot of the 9 quants available. Total memory needed is ~6.1GB once the KV cache and runtime are counted — the download size alone understates it.

How many phones can run DeepSeek R1 Distill 7B?

105 of the 140 phones we track have enough estimated usable memory at Q4_K_M; 91 also reach our usable-speed threshold of 3 tokens/s, and 21 run smoothly. Memory-fit alone does not mean a good experience.

Which Macs can run DeepSeek R1 Distill 7B?

54 of the 54 exact Mac configurations we track have enough estimated working memory. Each Mac uses the recommended Q4_K_M when it fits, or the largest smaller tracked quant that fits, and separates installed unified memory, the macOS reserve, and estimated speed.

What is DeepSeek R1 Distill 7B good for on a phone?

It's tagged for reasoning. At 7.6B parameters, it balances quality and speed for daily use.

Guides for DeepSeek

DeepSeek Harness Has 4 Modes. Which One Should You Use?
DeepSeek Harness vs Claude Code & Codex: Which Fits?

Similar models

DeepSeek R1 Distill 1.5BDeepSeek V4 Flash 0731Ling 3.0 TinyMistral 7B v0.3Llama 3.1 8B