What can NVIDIA RTX PRO 6000 Blackwell run for reasoning?

Build: RTX PRO 6000 Blackwell + Threadripper PRO + 128GB

Memory: 96 GB VRAM + 128 GB system RAM
Runner: llama.cpp / Ollama (CUDA)

Runs comfortably
200 models

Ranked by fit for reasoning use case + predicted speed. Click a row for VRAM breakdown.

#1DeepSeek R1 Distill Qwen 7B
7B
deepseek
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 13.8 GBHeadroom: 82.2 GB
ollama run deepseek-r1:7b
157
tok/s
Estimated
Weights
8.10 GB
KV cache
3.50 GB
Activations
0.41 GB
Runtime
1.80 GB
#2Phi-4 Reasoning 14B
14B
phi
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 78.4 GB
ollama run phi4-reasoning:14b
138
tok/s
Estimated
Weights
8.40 GB
KV cache
7.00 GB
Activations
0.43 GB
Runtime
1.80 GB
#3DeepSeek R1 Distill Qwen 14B
14B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 78.4 GB
ollama run deepseek-r1:14b
138
tok/s
Estimated
Weights
8.40 GB
KV cache
7.00 GB
Activations
0.43 GB
Runtime
1.80 GB
#4Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 85.0 GB
241
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Quant: Q4_K_MContext: 8,192VRAM: 11.6 GBHeadroom: 84.4 GB
214
tok/s
Estimated
Weights
5.00 GB
KV cache
4.50 GB
Activations
0.26 GB
Runtime
1.80 GB
#6RefinedNeuro RN TR R1
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 85.0 GB
ollama run RefinedNeuro/RN_TR_R1:latest
241
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
#7DeepSeek R1 Distill Llama 8B
8B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 85.3 GB
241
tok/s
Estimated
Weights
4.70 GB
KV cache
4.00 GB
Activations
0.24 GB
Runtime
1.80 GB
#8DeepSeek R1 Distill Mistral 24B
24B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 67.5 GB
80
tok/s
Estimated
Weights
14.00 GB
KV cache
12.00 GB
Activations
0.71 GB
Runtime
1.80 GB
Quant: Q4_K_MContext: 8,192VRAM: 35.3 GBHeadroom: 60.7 GB
62
tok/s
Estimated
Weights
17.10 GB
KV cache
15.50 GB
Activations
0.86 GB
Runtime
1.80 GB
#10QwQ 32B Preview
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 37.8 GBHeadroom: 58.2 GB
ollama run qwq:32b
60
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
1.80 GB
#11EXAONE 4.0.1 32B
32B
exaone
Quant: Q4_K_MContext: 8,192VRAM: 36.3 GBHeadroom: 59.7 GB
60
tok/s
Estimated
Weights
17.60 GB
KV cache
16.00 GB
Activations
0.89 GB
Runtime
1.80 GB
#12Qwen3 Swallow 32B RL v0.2
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 36.3 GBHeadroom: 59.7 GB
60
tok/s
Estimated
Weights
17.60 GB
KV cache
16.00 GB
Activations
0.89 GB
Runtime
1.80 GB

Runs with tradeoffs
12 models

Tight VRAM, partial CPU offload, or context-limited.

Nemotron 3 Super (120B-A12B)
120B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 92.4 GBHeadroom: 3.6 GB
  • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run nemotron3:super
16
tok/s
Estimated
Weights
72.00 GB
KV cache
15.00 GB
Activations
3.60 GB
Runtime
1.80 GB
GLM-5
200B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 152.8 GBHeadroom: 20.0 GB
  • Partial CPU offload: ~37% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3
tok/s
Estimated
Weights
120.00 GB
KV cache
25.00 GB
Activations
6.00 GB
Runtime
1.80 GB
Quant: Q4_K_MContext: 2,048VRAM: 167.6 GBHeadroom: 5.2 GB
  • Partial CPU offload: ~43% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3
tok/s
Estimated
Weights
129.80 GB
KV cache
29.50 GB
Activations
6.49 GB
Runtime
1.80 GB
Kimi K1.5
200B
moonshot
Quant: AWQ-INT4Context: 2,048VRAM: 147.6 GBHeadroom: 25.2 GB
  • Partial CPU offload: ~35% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
2
tok/s
Estimated
Weights
115.00 GB
KV cache
25.00 GB
Activations
5.75 GB
Runtime
1.80 GB
DeepSeek V2.5 236B
236B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 172.0 GBHeadroom: 0.8 GB
  • Partial CPU offload: ~44% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
29
tok/s
Estimated
Weights
134.00 GB
KV cache
29.50 GB
Activations
6.70 GB
Runtime
1.80 GB
DeepSeek Coder V2 236B
236B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 172.0 GBHeadroom: 0.8 GB
  • Partial CPU offload: ~44% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
29
tok/s
Estimated
Weights
134.00 GB
KV cache
29.50 GB
Activations
6.70 GB
Runtime
1.80 GB
GLM-5 Pro
144B
glm
Quant: AWQ-INT4Context: 8,192VRAM: 159.9 GBHeadroom: 12.9 GB
  • Partial CPU offload: ~40% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
25
tok/s
Estimated
Weights
82.00 GB
KV cache
72.00 GB
Activations
4.11 GB
Runtime
1.80 GB
DBRX Base
132B
dbrx
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 146.6 GBHeadroom: 26.2 GB
  • Partial CPU offload: ~34% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
20
tok/s
Estimated
Weights
75.00 GB
KV cache
66.00 GB
Activations
3.76 GB
Runtime
1.80 GB

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

+32 GB system RAM

~$80–150

Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 64 new comfortable, 14 new tradeoff

  • Qwen 3 0.6B
  • Llama 3.2 3B Instruct
  • Qwen 3 1.7B
  • Gemma 3 270M

Upgrade to NVIDIA H200 NVL (PCIe)

~$32000

141 GB VRAM (vs your 96 GB) plus a bandwidth jump from ~1792 GB/s to ~4800 GB/s.

Unlocks: 69 new comfortable

  • Qwen 3 0.6B
  • Llama 3.2 3B Instruct
  • Qwen 3 1.7B
  • Gemma 3 270M

Add a second NVIDIA RTX PRO 6000 Blackwell

~$8999

Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.

Unlocks: 78 new comfortable

  • Qwen 3 235B-A22B
  • Qwen 3 0.6B
  • GLM-5
  • Llama 3.2 3B Instruct

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)
1600B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.

Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.

Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.

DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.

DeepSeek V4 Flash (284B MoE)
284B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.

How to read these numbers

Measured here
Measured here - RunLocalAI ran this exact combo on owner hardware with public evidence.

Source-backed
Source-backed / community - a reproduced public source supports the speed, but it is not labeled as owner-measured.

Extrapolated
Extrapolated - predicted from a measured benchmark on similar-bandwidth hardware.

Estimated
Estimated - formula based on VRAM bandwidth and model architecture; not a benchmark row.

RunLocalAI Will-It-Run Framework →

Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.