 |
VOOZH | about |
CogVLM2 19B needs ~11.8 GB VRAM. Intel Arc B570 10GB has 10.0 GB. With Q2_K quantization, expect ~14 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
5.9 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
5.6 tok/s
TTFT
34396 ms
Safe context
4K
Memory
15.9 GB / 10.0 GB
Offload
40%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Runtime ecosystem is narrower than CUDA
Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Prefer CUDA if you want the path of least resistance
If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 6.6 tok/s | 15946 ms | 4K |
| Coding | F | Too heavy | 5.2 tok/s | 36976 ms | 4K |
| Agentic Coding | F | Too heavy | 4.2 tok/s | 66920 ms | 4K |
| Reasoning | F | Too heavy | 5.6 tok/s | 40650 ms | 4K |
| RAG | F | Too heavy | 4.2 tok/s | 83650 ms | 4K |
How CogVLM2 19B (19B params) fits at each quantization level on Intel Arc B570 10GB (10.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.4 GB | Low | F0 |
Q3_K_S | 3 | 9.3 GB | Low | F0 |
NVFP4 | 4 |
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 99Upgrade options
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$349 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$399 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$599 MSRP
| Medium |
| F0 |
Q4_K_M | 4 | 11.6 GB | Medium | F0 |
Q5_K_M | 5 | 13.7 GB | High | F0 |
Q6_K | 6 | 15.6 GB | High | F0 |
Q8_0 | 8 | 20.3 GB | Very High | F0 |
F16 | 16 | 38.9 GB | Maximum | F0 |
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
