What can NVIDIA RTX PRO 6000 Blackwell run for coding?
Build: RTX PRO 6000 Blackwell + Threadripper PRO + 128GB
Runs comfortably125 models
Ranked by fit for coding use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 86.3 GBollama run codegemma:7b231tok/sEstimated
ollama run codegemma:7bQuant: Q4_K_MContext: 8,192VRAM: 19.8 GBHeadroom: 76.2 GBollama run deepseek-coder-v2:16b101tok/sEstimated
ollama run deepseek-coder-v2:16bQuant: Q8_0Context: 8,192VRAM: 37.0 GBHeadroom: 59.0 GBollama run codestral:22b42tok/sEstimated
ollama run codestral:22bQuant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 85.2 GBollama run qwen2.5:7b131tok/sEstimated
ollama run qwen2.5:7bQuant: Q8_0Context: 8,192VRAM: 14.4 GBHeadroom: 81.6 GBollama run qwen3:8b115tok/sEstimated
ollama run qwen3:8bQuant: Q8_0Context: 8,192VRAM: 24.6 GBHeadroom: 71.4 GBollama run qwen3:14b66tok/sEstimated
ollama run qwen3:14bQuant: Q8_0Context: 8,192VRAM: 25.3 GBHeadroom: 70.7 GBollama run qwen2.5:14b66tok/sEstimated
ollama run qwen2.5:14bQuant: Q8_0Context: 8,192VRAM: 39.7 GBHeadroom: 56.3 GBollama run qwen2.5-coder:32b29tok/sEstimated
ollama run qwen2.5-coder:32bQuant: Q8_0Context: 8,192VRAM: 50.4 GBHeadroom: 45.6 GBollama run qwen3:30b31tok/sEstimated
ollama run qwen3:30bQuant: Q8_0Context: 8,192VRAM: 52.0 GBHeadroom: 44.0 GBollama run gemma4:31b30tok/sEstimated
ollama run gemma4:31bQuant: Q8_0Context: 8,192VRAM: 53.5 GBHeadroom: 42.5 GBollama run qwen3:32b29tok/sEstimated
ollama run qwen3:32bQuant: Q8_0Context: 8,192VRAM: 53.5 GBHeadroom: 42.5 GBollama run qwen2.5:32b29tok/sEstimated
ollama run qwen2.5:32bRuns with tradeoffs4 models
Tight VRAM, partial CPU offload, or context-limited.
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
28tok/sEstimated
- • Partial CPU offload: ~44% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
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
28tok/sEstimated
- • Partial CPU offload: ~44% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
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:123b13tok/sEstimated
- • Tight VRAM fit — only 2.2 GB headroom left for context growth
ollama run mistral-large:123bQuant: Q4_K_MContext: 8,192VRAM: 160.5 GBHeadroom: 12.3 GB- • Partial CPU offload: ~40% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run mixtral:8x22b4tok/sEstimated
- • Partial CPU offload: ~40% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run mixtral:8x22bWhat if you upgraded?
Hypothetical scenarios. We re-ran the compatibility engine for each.
+32 GB system RAM
Check the current price
Adds 32 GB to your CPU-offload working set. Helps when models don't quite fit in VRAM.
Unlocks: 28 new comfortable, 6 new tradeoff
- • Qwen 3 0.6B
- • Qwen 3 1.7B
- • Gemma 3 270M
- • SmolLM2 135M Instruct
Upgrade to NVIDIA H200
Launch MSRP $31,000 (2024). Check the current price.
141 GB VRAM (vs your 96 GB) plus a bandwidth jump from ~? GB/s to ~? GB/s.
Unlocks: 29 new comfortable
- • Qwen 3 0.6B
- • Qwen 3 1.7B
- • Gemma 3 270M
- • SmolLM2 135M Instruct
Add a second NVIDIA RTX PRO 6000 Blackwell
Launch MSRP $8,499 (2025). Check the current price.
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: 34 new comfortable
- • Qwen 3 235B-A22B
- • Qwen 3 0.6B
- • Qwen 3 1.7B
- • Gemma 3 270M
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
Won't runtop 5 popular models
Need more memory than you have. Shown for orientation.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
Not enough VRAM for these models? Rent a GPU by the hour
The models above need more memory than 96 GB VRAM + 128 GB system RAM. You can rent a GPU with enough VRAM by the hour to run one of them, or to test it before you buy hardware. For daily use, owning a card usually costs less over time.
RunPod
billed per GPU-hourHourly GPU pods, in community-cloud and secure-cloud tiers.
The two tiers run on different hosts and terms. Check which tier a pod is on before a long job.
Rent on RunPodVast.ai
billed per GPU-hourMarketplace of host-listed GPUs; price and reliability vary by host.
Host quality varies. Filter for verified hosts and check the host's reliability before a long run.
Rent on Vast.aiReferral links: RunLocalAI may earn a commission or account credits if you sign up and rent, at no extra cost to you. Hourly rates and which GPUs are listed change all the time, so check the provider's page before you start. Editorial opinions are independent of the referral relationship; see how we make money.
How to read these numbers
Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.