internlm2 5 20b chat needs ~12.5 GB VRAM. RTX 3060 12GB has 12.0 GB. With Q2_K quantization, expect ~18 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
4.9 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
7.1 tok/s
TTFT
27400 ms
Safe context
4K
Memory
16.9 GB / 12.0 GB
Offload
30%
This setup is broadly balanced for this model.
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.
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 | 8.2 tok/s | 12852 ms | 4K |
| Coding | F | Too heavy | 7.1 tok/s | 27400 ms | 4K |
| Agentic Coding | F | Too heavy | 5.4 tok/s | 52350 ms | 4K |
| Reasoning | F | Too heavy | 7.1 tok/s | 32381 ms | 4K |
| RAG | F | Too heavy | 5.4 tok/s | 65437 ms | 4K |
How internlm2 5 20b chat (20B params) fits at each quantization level on RTX 3060 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_KBest for your GPU | 2 | 7.8 GB | Low | C51 |
Q3_K_S | 3 | 9.8 GB | Low | F0 |
NVFP4 | 4 | 11.2 GB | Medium | F0 |
Q4_K_M | 4 | 12.2 GB | Medium | F0 |
Q5_K_M | 5 | 14.4 GB | High | F0 |
Q6_K | 6 | 16.4 GB | High | F0 |
Q8_0 | 8 | 21.4 GB | Very High | F0 |
F16 | 16 | 41.0 GB | Maximum | F0 |
Copy-paste commands to run internlm2 5 20b chat on your machine.
Run
lms load hf-bartowski--internlm2-5-20b-chat-gguf && lms server startUpgrade options
RTX 5060 Ti 16GBBest valueMakes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 108%.
~$449 MSRP
RTX 4060 Ti 16GBNVIDIA upgradeMakes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 54%.
~$499 MSRP
RTX 4000 Ada 20GBBudget pickMakes 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.
~$1,250 MSRP
RTX 4090 24GBBiggest leapMakes 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.
~$1,599 MSRP
Yes, RTX 3060 12GB can run internlm2 5 20b chat at Q2_K quantization (Runs with offload (needs ~0.3 GB host RAM)). The recommended Q4_K_M requires 16.9 GB which exceeds available memory, but at Q2_K it needs only 12.5 GB. Expected decode speed: 17.7 tok/s.
internlm2 5 20b chat (20B parameters) requires approximately 16.9 GB at Q4_K_M quantization. On RTX 3060 12GB, it fits at Q2_K using 12.5 GB.
The recommended quantization is Q4_K_M, but on RTX 3060 12GB the best fitting quantization is Q2_K, which uses 12.5 GB.
On RTX 3060 12GB, internlm2 5 20b chat achieves approximately 17.7 tokens per second decode speed with a time-to-first-token of 10944ms using Q2_K quantization.
For coding workloads, internlm2 5 20b chat on RTX 3060 12GB receives a F grade with 7.1 tok/s and 4K context.
On RTX 3060 12GB, internlm2 5 20b chat can safely use up to 12K tokens of context at Q2_K quantization. The model's official context limit is —, but available memory constrains the safe maximum.
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-bartowski--internlm2-5-20b-chat-gguf-on-rtx-3060-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: