selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

ByteDance-Seed logo

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

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.4 GBfits~52 tok/s
Q3_K_M Noticeable loss5.8 GBfits~35 tok/s
Q4_K_M pickSmall loss6.8 GBfits~28 tok/s
Q5_K_M Near-lossless7.7 GBtight~24 tok/s
Q6_K Near-lossless8.6 GBoffload~16 tok/s
Q8_0 Lossless11 GBoffload~8.5 tok/s
FP16 / BF16 Lossless19 GBoffload~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 →
ModelParamsBest quantMemorySpeedLicence
8.2BQ5_K_M≈7.3 GBFits in memory~26 tok/sCommercial OK
8BQ5_K_M≈7.1 GBFits in memory~26 tok/sConditions
7.6BQ6_K≈7.0 GBFits in memory~24 tok/sCommercial OK
8BQ5_K_M≈7.1 GBFits in memory~26 tok/sConditions
ibm-granite logogranite-4.2-8bibm-granite
8.8BQ4_K_M≈7.0 GBFits in memory~28 tok/sCommercial OK
ornith-ai logoOrnith-1.5-9Bornith-ai
9.7BQ4_K_M≈7.3 GBFits in memory~26 tok/sCommercial OK

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.