MiniCPM-V 2.6 8B needs ~8.9 GB VRAM. RX 6750 XT 12GB has 12.0 GB. With Q4_K_M quantization, expect ~50 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
50.4 tok/s
TTFT
3838 ms
Safe context
2K
Memory
8.9 GB / 12.0 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 | 50.4 tok/s | 2094 ms | 2K |
| Coding | S | Runs well | 50.4 tok/s | 3838 ms | 2K |
| Agentic Coding | A | Tight fit | 50.4 tok/s | 5583 ms | 2K |
| Reasoning | S | Runs well | 50.4 tok/s | 4536 ms | 2K |
| RAG | A | Tight fit | 50.4 tok/s | 6979 ms | 2K |
How MiniCPM-V 2.6 8B (8B params) fits at each quantization level on RX 6750 XT 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | A80 |
Q3_K_S | 3 | 3.9 GB | Low | A81 |
NVFP4 | 4 |
Copy-paste commands to run MiniCPM-V 2.6 8B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "openbmb/MiniCPM-V-2_6" \
--hf-file "MiniCPM-V-2_6-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 9B | S | 44.8 tok/s | ||
| 14B | A | 18.1 tok/s |
Yes, RX 6750 XT 12GB can run MiniCPM-V 2.6 8B with a S grade (Runs well). Expected decode speed: 50.4 tok/s.
MiniCPM-V 2.6 8B (8B parameters) requires approximately 8.9 GB of memory with Q4_K_M quantization.
The recommended quantization for MiniCPM-V 2.6 8B is Q4_K_M, which balances quality and memory efficiency.
On RX 6750 XT 12GB, MiniCPM-V 2.6 8B achieves approximately 50.4 tokens per second decode speed with a time-to-first-token of 3838ms using Q4_K_M quantization.
For coding workloads, MiniCPM-V 2.6 8B on RX 6750 XT 12GB receives a S grade with 50.4 tok/s and 2K context.
On RX 6750 XT 12GB, MiniCPM-V 2.6 8B can safely use up to 2K tokens of context. The model's official context limit is 2K, 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/minicpm-v-2.6-8b-on-rx-6750-xt-12gb" 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 |
| A82 |
Q4_K_M | 4 | 4.9 GB | Medium | A82 |
Q5_K_M | 5 | 5.8 GB | High | A83 |
Q6_K | 6 | 6.6 GB | High | A83 |
Q8_0Best for your GPU | 8 | 8.6 GB | Very High | A82 |
F16 | 16 | 16.4 GB | Maximum | F0 |
| 14.7B | A | 14.6 tok/s |
| 14B | A | 18 tok/s |
| 14B | A | 16.4 tok/s |