InternVL2 8B needs ~10.9 GB VRAM. Radeon AI PRO R9700 32GB has 32.0 GB. With Q4_K_M quantization, expect ~83 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
83.2 tok/s
TTFT
2327 ms
Safe context
8K
Memory
10.9 GB / 32.0 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 | 83.2 tok/s | 1270 ms | 8K |
| Coding | A | Runs well | 83.2 tok/s | 2327 ms | 8K |
| Agentic Coding | A | Runs well | 83.2 tok/s | 3385 ms | 8K |
| Reasoning | A | Runs well | 83.2 tok/s | 2751 ms | 8K |
| RAG | A | Runs well | 83.2 tok/s | 4232 ms | 8K |
How InternVL2 8B (8B params) fits at each quantization level on Radeon AI PRO R9700 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | A75 |
Q3_K_S | 3 | 3.9 GB | Low | A76 |
NVFP4 | 4 | 4.5 GB | Medium | A76 |
Q4_K_M | 4 | 4.9 GB | Medium | A76 |
Q5_K_M | 5 | 5.8 GB | High | A76 |
Q6_K | 6 | 6.6 GB | High | A77 |
Q8_0 | 8 | 8.6 GB | Very High | A77 |
F16Best for your GPU | 16 | 16.4 GB | Maximum | A81 |
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 | 57.1 tok/s | |
| Qwen 3.5 27B | 27B | S | 24.8 tok/s | |
| Qwen 3.6 27B | 27B | S | 18.8 tok/s | |
| Qwen 3.6 35B A3B | 35B | S | 48 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 59.1 tok/s |
Yes, Radeon AI PRO R9700 32GB can run InternVL2 8B with a A grade (Runs well). Expected decode speed: 83.2 tok/s.
InternVL2 8B (8B parameters) requires approximately 10.9 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 Radeon AI PRO R9700 32GB, InternVL2 8B achieves approximately 83.2 tokens per second decode speed with a time-to-first-token of 2327ms using Q4_K_M quantization.
For coding workloads, InternVL2 8B on Radeon AI PRO R9700 32GB receives a A grade with 83.2 tok/s and 8K context.
On Radeon AI PRO R9700 32GB, 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-radeon-ai-pro-r9700-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: