Can the RTX 4060 run Cola2?
Cola2·8.8B·GeForce RTX 4060·8 GB VRAM
Saved in this browser, used on every model page.
Yes
Yes. The RTX 4060 runs Cola2 fully in VRAM at Q4_K_M (about 6.8 GB of 8.0 GB), at roughly 28 tokens/s.
- best quant
- Q4_K_M
- needs
- 6.8 GB
- usable
- 8.0 GB
- est. speed
- ~28 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Cola2 page →
Every quantisation of Cola2 on the RTX 4060
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 4.4 GB | fits | ~52 tok/s |
| Q3_K_M | 5.8 GB | fits | ~35 tok/s |
| Q4_K_M pick | 6.8 GB | fits | ~28 tok/s |
| Q5_K_M | 7.7 GB | tight | ~24 tok/s |
| Q6_K | 8.6 GB | offload | ~16 tok/s |
| Q8_0 | 11 GB | offload | ~8.5 tok/s |
| FP16 / BF16 | 19 GB | offload | ~2.8 tok/s |
Speed is a bandwidth-based estimate for generating text (272 GB/s); prompt processing and long contexts are slower.
Measured speed on the RTX 4060
No community reports for this pair yet.
Report your own speed →Run Cola2 on the RTX 4060
Transformers · Chat with the pipeline APIdocs
from transformers import pipeline
pipe = pipeline("text-generation", model="ByteDance-Seed/Cola2", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])Chat models that fit the RTX 4060 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 8.2B | Q5_K_M | ≈7.3 GBFits in memory | ~26 tok/s | |
| 8B | Q5_K_M | ≈7.1 GBFits in memory | ~26 tok/s | |
| 7.6B | Q6_K | ≈7.0 GBFits in memory | ~24 tok/s | |
| 8B | Q5_K_M | ≈7.1 GBFits in memory | ~26 tok/s | |
| 8.8B | Q4_K_M | ≈7.0 GBFits in memory | ~28 tok/s | |
| 9.7B | Q4_K_M | ≈7.3 GBFits in memory | ~26 tok/s |
Other GPUs that run Cola2
Frequently asked questions
- Can the RTX 4060 run Cola2?
- Yes. The RTX 4060 runs Cola2 fully in VRAM at Q4_K_M (about 6.8 GB of 8.0 GB), at roughly 28 tokens/s.
- How fast does Cola2 run on the RTX 4060?
- An estimate from memory bandwidth gives about 28 tokens/s at Q4_K_M.
- Which quantisation of Cola2 should I use on the RTX 4060?
- Q4_K_M: the largest one that fits. Expected quality: small loss compared with the full-precision weights.
Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.