InternVL2 8B needs ~10.1 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~51 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
54.2 tok/s
TTFT
3569 ms
Safe context
8K
Memory
10.1 GB / 24.0 GB
The raw memory story may look fine, but the software ecosystem is still a constraint here.
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.
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 50.5 tok/s | 2093 ms | 8K |
| Coding | A | Runs well | 50.5 tok/s | 3837 ms | 8K |
| Agentic Coding | A | Runs well | 50.5 tok/s | 5581 ms | 8K |
| Reasoning | A | Runs well | 50.5 tok/s | 4534 ms | 8K |
| RAG | A | Runs well | 50.5 tok/s | 6976 ms | 8K |
How InternVL2 8B (8B params) fits at each quantization level on Intel Arc Pro B60 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | A77 |
Q3_K_S | 3 | 3.9 GB | Low | A77 |
NVFP4 | 4 |
Copy-paste commands to run InternVL2 8B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "OpenGVLab/InternVL2-8B" \
--hf-file "InternVL2-8B-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 37.2 tok/s | |
| Qwen 3.5 27B | 27B | S | 16.1 tok/s |
Yes, Intel Arc Pro B60 24GB can run InternVL2 8B with a A grade (Runs well). Expected decode speed: 50.5 tok/s.
InternVL2 8B (8B parameters) requires approximately 10.1 GB of memory with Q4_K_M quantization.
The recommended quantization for InternVL2 8B is Q4_K_M, which balances quality and memory efficiency.
On Intel Arc Pro B60 24GB, InternVL2 8B achieves approximately 50.5 tokens per second decode speed with a time-to-first-token of 3837ms using Q4_K_M quantization.
For coding workloads, InternVL2 8B on Intel Arc Pro B60 24GB receives a A grade with 50.5 tok/s and 8K context.
On Intel Arc Pro B60 24GB, InternVL2 8B 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/internvl2-8b-on-arc-pro-b60-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
4.5 GB |
| Medium |
| A78 |
Q4_K_M | 4 | 4.9 GB | Medium | A78 |
Q5_K_M | 5 | 5.8 GB | High | A78 |
Q6_K | 6 | 6.6 GB | High | A79 |
Q8_0 | 8 | 8.6 GB | Very High | A80 |
F16Best for your GPU | 16 | 16.4 GB | Maximum | A82 |
| Qwen 3.6 27B | 27B | S | 12.3 tok/s |
| Qwen 3.6 35B A3B | 35B | A | 16.6 tok/s |
| Qwen3-VL 30B A3B Instruct | 30B | S | 38.5 tok/s |
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.
Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.