CogVLM2 19B needs ~24.5 GB VRAM. RTX PRO 6000 Blackwell Workstation Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~140 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
139.6 tok/s
TTFT
1387 ms
Safe context
8K
Memory
24.5 GB / 96.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 139.6 tok/s | 756 ms | 8K |
| Coding | A | Runs well | 139.6 tok/s | 1387 ms | 8K |
| Agentic Coding | A | Runs well | 139.6 tok/s | 2017 ms | 8K |
| Reasoning | A | Runs well | 139.6 tok/s | 1639 ms | 8K |
| RAG | A | Runs well | 139.6 tok/s | 2521 ms | 8K |
How CogVLM2 19B (19B params) fits at each quantization level on RTX PRO 6000 Blackwell Workstation Edition 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.4 GB | Low | A72 |
Q3_K_S | 3 | 9.3 GB | Low | A73 |
NVFP4 | 4 | 10.6 GB | Medium | A73 |
Q4_K_M | 4 | 11.6 GB | Medium | A73 |
Q5_K_M | 5 | 13.7 GB | High | A73 |
Q6_K | 6 | 15.6 GB | High | A73 |
Q8_0 | 8 | 20.3 GB | Very High | A74 |
F16Best for your GPU | 16 | 38.9 GB | Maximum | A77 |
Copy-paste commands to run CogVLM2 19B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "THUDM/cogvlm2-llama3-chat-19B" \
--hf-file "cogvlm2-llama3-chat-19B-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Devstral 2 123B Instruct | 123B | S | 21.8 tok/s | |
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 227.6 tok/s | |
| Qwen 3.5 27B | 27B | S | 98.7 tok/s | |
| Qwen 3.6 27B | 27B | S | 61.5 tok/s | |
| Qwen 3.5 122B A10B | 122B | S | 60.5 tok/s |
Yes, RTX PRO 6000 Blackwell Workstation Edition 96GB can run CogVLM2 19B with a A grade (Runs well). Expected decode speed: 139.6 tok/s.
CogVLM2 19B (19B parameters) requires approximately 24.5 GB of memory with Q4_K_M quantization.
The recommended quantization for CogVLM2 19B is Q4_K_M, which balances quality and memory efficiency.
On RTX PRO 6000 Blackwell Workstation Edition 96GB, CogVLM2 19B achieves approximately 139.6 tokens per second decode speed with a time-to-first-token of 1387ms using Q4_K_M quantization.
For coding workloads, CogVLM2 19B on RTX PRO 6000 Blackwell Workstation Edition 96GB receives a A grade with 139.6 tok/s and 8K context.
On RTX PRO 6000 Blackwell Workstation Edition 96GB, CogVLM2 19B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/cogvlm2-19b-on-rtx-pro-6000-blackwell-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: