DeepSeek-R1 (671B MoE) — VRAM Requirements, Quantization Matrix & GPU Guide
DeepSeek-R1 (671B MoE) (DeepSeek, MIT) is a Mixture-of-Experts (MoE) architecture with 671B resident parameters (37B active per token), 61 layers, and Multi-head Latent Attention (MLA) supporting up to 163,840 context tokens.
Interactive DeepSeek-R1 (671B MoE) Memory & Context Simulator
Precision & Quantization VRAM Matrix (8K / 32K / 128K Context)
| Precision / Format | Effective bpw | Weights Only | Total @ 8K ctx | Total @ 32K ctx | Total @ 128K ctx | Recommended Tier (@ 32K) |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 bpw | 1249.83 GB | 1289.19 GB | 1290.80 GB | 1297.24 GB | 8× NVIDIA H100 80GB |
| FP8 | 8.50 bpw | 663.97 GB | 685.76 GB | 687.37 GB | 693.80 GB | 8× NVIDIA H100 80GB |
| Q8_0 | 8.50 bpw | 663.97 GB | 685.76 GB | 687.37 GB | 693.80 GB | 8× NVIDIA H100 80GB |
| Q6_K | 6.56 bpw | 512.43 GB | 529.67 GB | 531.28 GB | 537.71 GB | 8× NVIDIA H100 80GB |
| Q5_K_M | 5.69 bpw | 444.47 GB | 459.67 GB | 461.28 GB | 467.71 GB | 8× NVIDIA H100 80GB |
| Q4_K_M | 4.85 bpw | 378.86 GB | 392.09 GB | 393.69 GB | 400.13 GB | 8× NVIDIA H100 80GB |
| AWQ INT4 | 4.50 bpw | 351.52 GB | 363.93 GB | 365.53 GB | 371.97 GB | Mac Studio 512GB |
| IQ4_XS | 4.25 bpw | 331.99 GB | 343.81 GB | 345.42 GB | 351.85 GB | Mac Studio 512GB |
Hardware Compatibility & Decode Speed (DeepSeek-R1 (671B MoE) @ Q4_K_M, 32K Context)
| Hardware Tier | Memory & Bandwidth | Required (32K) | Fit Verdict | Est. Decode Speed |
|---|---|---|---|---|
| RTX 3090 24GB | 24 GB · 936 GB/s | 393.69 GB (1640%) | Out of Memory (OOM) | — |
| RTX 4090 24GB | 24 GB · 1008 GB/s | 393.69 GB (1640%) | Out of Memory (OOM) | — |
| RTX 5090 32GB | 32 GB · 1792 GB/s | 393.69 GB (1230%) | Out of Memory (OOM) | — |
| Apple M-Max 64GB | 64 GB · 546 GB/s | 387.67 GB (606%) | Out of Memory (OOM) | — |
| Mac Studio 128GB | 128 GB · 546 GB/s | 387.67 GB (303%) | Out of Memory (OOM) | — |
| Mac Studio 192GB | 192 GB · 800 GB/s | 387.67 GB (202%) | Out of Memory (OOM) | — |
| NVIDIA A100 80GB | 80 GB · 2039 GB/s | 393.69 GB (492%) | Out of Memory (OOM) | — |
| NVIDIA H100 80GB | 80 GB · 3350 GB/s | 393.69 GB (492%) | Out of Memory (OOM) | — |
Verified Transformer Architecture Parameters
- Checkpoint ID
- deepseek-ai/DeepSeek-R1
- Ollama Tag
- deepseek-r1:671b
- License / Release
- MIT · 2025-Q1
- Topology & Attention
- Mixture-of-Experts (MoE)
- Attention Mechanism
- Multi-head Latent Attention (MLA)
- Total Params (B)
- 671B
- Active Params / Token (B)
- 37B
- Hidden Layers / Hidden Size
- 61 / 7168
- Query Heads / KV Heads
- 128Q / 128KV (d=128)
- MLA kv_lora_rank / rope_dim
- 512 / 64
- MoE Routed Experts
- 8 active / 256 total
- Vocab / Max Position
- 129,280 / 163,840
Quantized formats store per-block scale factors and zero-points alongside packed integer weights. A 4-bit GGUF Q4_K_M checkpoint averages 4.85 effective bits per parameter (not 4.00), while Q8_0 averages 8.50 bpw. For Mixture-of-Experts models, all routed and shared experts remain resident in memory to prevent token-by-token host paging.
Standard Grouped-Query Attention allocates 2 × L × H_kv × d_head × S × B × bytes_kv across layers. DeepSeek Multi-head Latent Attention (MLA) compresses keys and values into L × (d_kv_lora + d_qk_rope) × S × B × bytes_kv, slashing long-context memory by over 90%. Hybrid sliding-window models cap local-attention layers at min(S, window_size) while scaling global layers linearly with S.
Quick-Start vLLM & Ollama Commands for DeepSeek-R1 (671B MoE)
vllm serve deepseek-ai/DeepSeek-R1 \
--tensor-parallel-size 8 \
--max-model-len 32768 \
--max-num-seqs 8 \
--gpu-memory-utilization 0.80 \
--kv-cache-dtype fp8 \
--enable-expert-parallel \
--enable-prefix-caching \
--port 8000# Save as Modelfile, then run: ollama create deepseek-r1-671b-custom -f Modelfile
FROM deepseek-r1:671b
PARAMETER num_ctx 32768
PARAMETER num_batch 512
PARAMETER flash_attn true
# Environment variables for ollama serve:
# OLLAMA_NUM_PARALLEL=8 OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q8_0 ollama serveCompare Sibling & Similar-Scale Open-Weight Models
DeepSeek-V3-0324 (671B MoE)
DeepSeek · 671B (MLA)
DeepSeek-R1-Distill-Llama-70B
DeepSeek · 70.6B (GQA)
DeepSeek-R1-Distill-Qwen-32B
DeepSeek · 32.8B (GQA)
Llama 3.1 405B Instruct
Meta Llama · 405B (GQA)
Llama 4 Maverick (400B / 17B-128E MoE)
Meta Llama · 402B (GQA)
Qwen3-235B-A22B (MoE)
Qwen · 235B (GQA)