DeepSeek · MIT · HF: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
DeepSeek-R1 Distill Qwen 32B — VRAM, KV Cache & Hardware Matrix
Serverless API Rate
$0.10 in / $0.30 out per 1M
Parameters
32.8B Dense
Attention
GQA (8 KV / 40 Q)
Layers × Hidden
64 × 5120
Max Native Context
128k tokens
MoE Experts
N/A (Dense)
Quantization Memory Footprint
| Quantization | BPW | Weights Only | Total @ 8k Ctx | Total @ 32k Ctx | Quality |
|---|---|---|---|---|---|
| FP16 | 16.00 | 62.32 GiB | 65.77 GiB | 71.77 GiB | Lossless Reference |
| Q8_0 | 8.50 | 33.11 GiB | 36.56 GiB | 42.56 GiB | Near-Lossless |
| Q6_K | 6.57 | 25.59 GiB | 29.04 GiB | 35.04 GiB | High Precision |
| Q5_K_M | 5.69 | 22.16 GiB | 25.61 GiB | 31.61 GiB | Balanced High |
| Q4_K_M | 4.85 | 18.89 GiB | 22.34 GiB | 28.34 GiB | Recommended 4-bit |
| MLX_4BIT | 4.50 | 17.53 GiB | 20.98 GiB | 26.98 GiB | Apple Silicon Optimized |
| IQ4_XS | 4.25 | 16.55 GiB | 20.01 GiB | 26.01 GiB | Compact 4-bit |
| Q3_K_M | 3.91 | 15.23 GiB | 18.68 GiB | 24.68 GiB | Aggressive Compression |
Hardware Compatibility & Speed Leaderboard (Q4_K_M @ 32k Context)
| Hardware | Status | Total / Limit | Decode | TTFT (4k) | Max Safe Ctx | Inspect |
|---|---|---|---|---|---|---|
| Cloud NVIDIA H200 SXM (141 GB) | COMFORTABLE | 28.3 / 140.4 GiB | 139.7 tok/s | 0.43s | 128k | Simulate → |
| Cloud NVIDIA H100 SXM (80 GB) | COMFORTABLE | 28.3 / 79.4 GiB | 97.5 tok/s | 0.43s | 128k | Simulate → |
| Cloud NVIDIA A100 SXM (80 GB) | COMFORTABLE | 28.3 / 79.4 GiB | 57.9 tok/s | 1.35s | 128k | Simulate → |
| NVIDIA RTX PRO 6000 Blackwell (96 GB) | COMFORTABLE | 28.3 / 95.0 GiB | 52.1 tok/s | 1.68s | 128k | Simulate → |
| Cloud NVIDIA L40S (48 GB) | COMFORTABLE | 28.3 / 47.4 GiB | 24.5 tok/s | 1.21s | 108k | Simulate → |
| Apple Mac Studio M3 Ultra (256 GB) | COMFORTABLE | 28.1 / 199.7 GiB | 22.1 tok/s | 8.35s | 128k | Simulate → |
| Apple Mac Studio M3 Ultra (512 GB) | COMFORTABLE | 28.1 / 399.4 GiB | 22.1 tok/s | 8.35s | 128k | Simulate → |
| 2x NVIDIA RTX 3090 Rig (48 GB) | COMFORTABLE | 28.3 / 46.6 GiB | 21.8 tok/s | 7.85s | 105k | Simulate → |
| Apple Mac Studio M2 Ultra (192 GB) | COMFORTABLE | 28.1 / 149.8 GiB | 21.6 tok/s | 9.22s | 128k | Simulate → |
| Apple Mac Studio M4 Max (64 GB) | COMFORTABLE | 28.1 / 49.9 GiB | 14.6 tok/s | 12.70s | 128k | Simulate → |
| Apple Mac Studio M4 Max (128 GB) | COMFORTABLE | 28.1 / 99.8 GiB | 14.6 tok/s | 12.70s | 128k | Simulate → |
| Apple MacBook Pro M3 Max (64 GB) | COMFORTABLE | 28.1 / 49.9 GiB | 10.5 tok/s | 17.02s | 128k | Simulate → |
| Apple MacBook Pro M3 Max (128 GB) | COMFORTABLE | 28.1 / 99.8 GiB | 10.5 tok/s | 17.02s | 128k | Simulate → |
| Apple Mac Mini M4 Pro (48 GB) | COMFORTABLE | 28.1 / 37.4 GiB | 7.0 tok/s | 26.24s | 88k | Simulate → |
| Apple Mac Mini M4 Pro (64 GB) | COMFORTABLE | 28.1 / 49.9 GiB | 7.0 tok/s | 26.24s | 128k | Simulate → |
| Ryzen AI Max+ 395 Strix Halo (128 GB) | COMFORTABLE | 28.1 / 96.0 GiB | 6.6 tok/s | 9.45s | 128k | Simulate → |
| Ryzen AI Max+ 395 Strix Halo (64 GB) | COMFORTABLE | 28.1 / 48.0 GiB | 6.6 tok/s | 9.45s | 128k | Simulate → |
| Ryzen AI 9 HX 370 Mini-PC (64 GB) | COMFORTABLE | 28.1 / 48.0 GiB | 2.9 tok/s | 27.06s | 128k | Simulate → |
| NVIDIA RTX 5090 (32 GB) | TIGHT | 28.3 / 31.0 GiB | 50.9 tok/s | 2.09s | 43k | Simulate → |
| NVIDIA RTX 4090 (24 GB) | OOM | 28.3 / 23.0 GiB | OOM | — | 11k | Simulate → |
| NVIDIA RTX 5080 (16 GB) | OOM | 28.3 / 15.0 GiB | OOM | — | OOM | Simulate → |
| NVIDIA RTX 3090 (24 GB Used) | OOM | 28.3 / 23.0 GiB | OOM | — | 11k | Simulate → |
| NVIDIA RTX 5070 Ti (16 GB) | OOM | 28.3 / 15.0 GiB | OOM | — | OOM | Simulate → |
| AMD Radeon RX 7900 XTX (24 GB) | OOM | 28.3 / 23.0 GiB | OOM | — | 11k | Simulate → |
| NVIDIA RTX 5060 Ti (16 GB) | OOM | 28.3 / 15.0 GiB | OOM | — | OOM | Simulate → |
| NVIDIA RTX 3060 (12 GB) | OOM | 28.3 / 11.0 GiB | OOM | — | OOM | Simulate → |
| Apple Mac Mini M4 (16 GB) | OOM | 28.1 / 10.0 GiB | OOM | — | OOM | Simulate → |
| Apple Mac Mini M4 (24 GB) | OOM | 28.1 / 18.0 GiB | OOM | — | OOM | Simulate → |
Interactive DeepSeek-R1 Distill Qwen 32B Simulator
32.8B Dense · GQA
1792 GB/s · 250 TFLOPS
3. Weight Quantization
4.85 bpw
4. KV Cache
32,768 tok
Compute Roofline
COMFORTABLE FIT Memory-Bandwidth Bound
Max Safe Ctx: 128k
Memory Allocation Footprint 28.34 / 95.00 GiB usable
Weights: 18.89 GiB
KV Cache: 8.00 GiB
Overhead: 1.45 GiB
Headroom: 66.66 GiB
Decode Speed
52.1
tok/s (batch=1)
Prefill Speed
2490
prompt tok/s
TTFT Latency
1.68s
for 4,096 tok
Active Params
32.8B
of 32.8B total
llama.cpp Server Command
llama-server -hf deepseek-ai/DeepSeek-R1-Distill-Qwen-32B:Q4_K_M -ngl 99 -fa on -c 32768 --port 8080| Context | KV Cache | Total VRAM | Decode | Status |
|---|---|---|---|---|
| 4k | 1.00 GiB | 20.99 GiB | 70.5 tok/s | COMFORTABLE |
| 8k | 2.00 GiB | 22.34 GiB | 67.1 tok/s | COMFORTABLE |
| 16k | 4.00 GiB | 24.34 GiB | 61.3 tok/s | COMFORTABLE |
| 32k | 8.00 GiB | 28.34 GiB | 52.1 tok/s | COMFORTABLE |
| 64k | 16.00 GiB | 36.34 GiB | 40.2 tok/s | COMFORTABLE |
| 128k | 32.00 GiB | 52.34 GiB | 27.6 tok/s | COMFORTABLE |
Buy-vs-Cloud-vs-API Monthly TCO Break-Even
USE SERVERLESS APIOwn Hardware/mo
$167.91
85.5h active + power
Cloud GPU/mo
$181.88
@$1.85/hr spot/pod
Serverless API/mo
$9.50
API cheaper
Recommended Hardware & Cloud Deployment
Contextual to fit statusEngineering FAQ — DeepSeek-R1 Distill Qwen 32B
How much VRAM does DeepSeek-R1 Distill Qwen 32B require in Q4_K_M?
DeepSeek-R1 Distill Qwen 32B weights occupy 18.89 GiB in Q4_K_M. Including 32k FP16 KV cache and runtime buffers, total memory is 28.34 GiB.
What is the cheapest local hardware that runs DeepSeek-R1 Distill Qwen 32B?
NVIDIA RTX PRO 6000 Blackwell (96 GB) (96 GB) runs DeepSeek-R1 Distill Qwen 32B Q4_K_M at ~52.1 tok/s decode and 1.68s TTFT.
How does DeepSeek-R1 Distill Qwen 32B scale KV cache at long context?
DeepSeek-R1 Distill Qwen 32B uses GQA with 8 KV heads across 64 layers (128 head_dim).