What can NVIDIA RTX PRO 6000 Blackwell run for long context?

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

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

Runs comfortably
223 models

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

#1Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.4 GBHeadroom: 81.6 GB
ollama run qwen3:8b
137
tok/s
Estimated
Weights
8.20 GB
KV cache
4.00 GB
Activations
0.42 GB
Runtime
1.80 GB
#2Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 85.2 GB
ollama run qwen2.5:7b
157
tok/s
Estimated
Weights
8.10 GB
KV cache
0.47 GB
Activations
0.41 GB
Runtime
1.80 GB
#3Gemma 4 E4B (Effective 4B)
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 87.6 GB
ollama run gemma4:e4b
274
tok/s
Estimated
Weights
4.40 GB
KV cache
2.00 GB
Activations
0.23 GB
Runtime
1.80 GB
#4Phi-3.5 Mini Instruct
3.8B
phi
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 8.0 GBHeadroom: 88.0 GB
ollama run phi3.5:3.8b
288
tok/s
Estimated
Weights
4.10 GB
KV cache
1.90 GB
Activations
0.21 GB
Runtime
1.80 GB
Quant: Q4_K_MContext: 8,192VRAM: 10.4 GBHeadroom: 85.6 GB
241
tok/s
Estimated
Weights
4.40 GB
KV cache
4.00 GB
Activations
0.23 GB
Runtime
1.80 GB
#6Falcon Mamba 7B
7B
falcon
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 86.3 GB
276
tok/s
Estimated
Weights
4.20 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.80 GB
#7Jamba 1.5 Mini
52B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 59.3 GBHeadroom: 36.7 GB
161
tok/s
Estimated
Weights
30.00 GB
KV cache
26.00 GB
Activations
1.51 GB
Runtime
1.80 GB
#8Codestral Mamba 7B
7B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 86.3 GB
276
tok/s
Estimated
Weights
4.20 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.80 GB
Quant: Q4_K_MContext: 8,192VRAM: 5.3 GBHeadroom: 90.7 GB
643
tok/s
Estimated
Weights
1.90 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 84.9 GB
241
tok/s
Estimated
Weights
5.00 GB
KV cache
4.00 GB
Activations
0.26 GB
Runtime
1.80 GB
#11Nemotron 3 Nano (30B-A3B)
30B
other
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 50.4 GBHeadroom: 45.6 GB
ollama run nemotron3:nano
37
tok/s
Estimated
Weights
32.00 GB
KV cache
15.00 GB
Activations
1.61 GB
Runtime
1.80 GB
#12Mistral Nemo 12B Instruct
12B
mistral
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 21.5 GBHeadroom: 74.5 GB
ollama run mistral-nemo:12b
91
tok/s
Estimated
Weights
13.00 GB
KV cache
6.00 GB
Activations
0.66 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
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
Quant: Q4_K_MContext: 2,048VRAM: 93.8 GBHeadroom: 2.2 GB
  • Tight VRAM fit — only 2.2 GB headroom left for context growth
ollama run mistral-large:123b
16
tok/s
Estimated
Weights
73.00 GB
KV cache
15.38 GB
Activations
3.65 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
DBRX Instruct
132B
dbrx
Commercial OK
Quant: AWQ-INT4Context: 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
12
tok/s
Estimated
Weights
75.00 GB
KV cache
66.00 GB
Activations
3.76 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

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: 41 new comfortable, 14 new tradeoff

  • Qwen 3 0.6B
  • Qwen 3 1.7B
  • Gemma 3 270M
  • SmolLM2 135M Instruct

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: 46 new comfortable

  • Qwen 3 0.6B
  • Qwen 3 1.7B
  • Gemma 3 270M
  • SmolLM2 135M Instruct

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: 55 new comfortable

  • Qwen 3 235B-A22B
  • Qwen 3 0.6B
  • GLM-5
  • Qwen 3 1.7B

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.