CogVLM2 19B needs ~17.3 GB VRAM. RTX 3090 Ti 24GB has 24.0 GB. With Q4_K_M quantization, expect ~60 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
59.5 tok/s
TTFT
3255 ms
Safe context
8K
Memory
17.3 GB / 24.0 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 | S | Runs well | 59.5 tok/s | 1775 ms | 8K |
| Coding | S | Runs well | 59.5 tok/s | 3255 ms | 8K |
| Agentic Coding | S | Tight fit | 59.5 tok/s | 4734 ms | 8K |
| Reasoning | S | Runs well | 59.5 tok/s | 3846 ms | 8K |
| RAG | S | Tight fit | 59.5 tok/s | 5918 ms | 8K |
How CogVLM2 19B (19B params) fits at each quantization level on RTX 3090 Ti 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.4 GB | Low | A80 |
Q3_K_S | 3 | 9.3 GB | Low | A82 |
NVFP4 | 4 | 10.6 GB | Medium | A82 |
Q4_K_M | 4 | 11.6 GB | Medium | A83 |
Q5_K_M | 5 | 13.7 GB | High | A83 |
Q6_KBest for your GPU | 6 | 15.6 GB | High | A83 |
Q8_0 | 8 | 20.3 GB | Very High | F0 |
F16 | 16 | 38.9 GB | Maximum | F0 |
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 |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 71.4 tok/s | |
| Qwen 3.5 27B | 27B | S | 32 tok/s | |
| Qwen 3.6 27B | 27B | S | 20.2 tok/s | |
| Qwen 3.6 35B A3B | 35B | A | 46.6 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 111.9 tok/s |
Yes, RTX 3090 Ti 24GB can run CogVLM2 19B with a S grade (Runs well). Expected decode speed: 59.5 tok/s.
CogVLM2 19B (19B parameters) requires approximately 17.3 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 3090 Ti 24GB, CogVLM2 19B achieves approximately 59.5 tokens per second decode speed with a time-to-first-token of 3255ms using Q4_K_M quantization.
For coding workloads, CogVLM2 19B on RTX 3090 Ti 24GB receives a S grade with 59.5 tok/s and 8K context.
On RTX 3090 Ti 24GB, 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-3090-ti-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: