Can Ornith 1.0 9B run on RTX 3050 8GB?

YES — With Q5_K_M

B66Good

Estimated from fit model

Ornith 1.0 9B needs ~9.3 GB VRAM. RTX 3050 8GB has 8.0 GB. With Q5_K_M quantization, expect ~13 tok/s.

Runtime: OllamaCapacity: OffloadBandwidth: Very lowStack: BasicBottleneck: Host offload

Operating mode

Choose the run profile you care about

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.

Ornith 1.0 9B at Q4_K_M needs 9.7 GB — too much for RTX 3050 8GB (8.0 GB). Runs at Q5_K_M (9.3 GB) with high quality. 7 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 8.2 GB, 19.6 tok/s, Runs with offload (needs ~0.2 GB host RAM)

8.2 GB required8.0 GB available

102% VRAM needed

0.2 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~0.2 GB host RAM)

Decode

19.6 tok/s

TTFT

9866 ms

Safe context

Memory

8.2 GB / 8.0 GB

Memory breakdown

Weights5.7 GB

KV Cache0.5 GB

Runtime1.2 GB

Headroom0.8 GB

See how fast it feels

See how fast it feelsOrnith 1.0 9B on RTX 3050 8GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers))  # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
    """Sort a list using the quicksort algorithm.

    Args:
        arr: List of integers to sort.

    Returns:
        A new sorted list.
    """
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 19.6 tok/s decode · 9.9s TTFT (warm) · 49 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 0.9 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Very compromised	16.2 tok/s	6532 ms	4K
Coding	F	Too heavy	12.9 tok/s	14978 ms	4K
Agentic Coding	F	Too heavy	8.8 tok/s	32069 ms	4K
Reasoning	F	Too heavy	12.9 tok/s	17701 ms	4K
RAG	F	Too heavy	8.8 tok/s	40086 ms	4K

Inference speed

Ornith 1.0 9B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Ornith 1.0 9B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~132 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	131.6	Fits
RTX 4090 24GB	24 GB	Q4_K_M	131.6	Fits
RTX 3090 24GB	24 GB	Q4_K_M	122.8	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	114.5	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	84.9	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	79.1	Fits
RTX 4070 12GB	12 GB	Q4_K_M	70.9	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	70.3	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	65.9	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	62.5	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	53.3	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	45.0	Fits
RTX 3060 12GB	12 GB	Q4_K_M	44.5	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	41.2	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	36.3	Fits
RTX 4060 8GB	8 GB	Q4_K_M	26.4	Offloads

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Ornith 1.0 9B (9.399999618530273B params) fits at each quantization level on RTX 3050 8GB (8.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q1_0_G128	1.125	1.4 GB	Very Low	A78
Q2_0_G128	1.71	2.5 GB	Low	A81
Q2_K	2	3.7 GB	Low	A81
Q3_K_S	3	4.6 GB	Low	A81
NVFP4Best for your GPU	4	5.3 GB	Medium	A81
Q4_K_M	4	5.7 GB	Medium	F0
Q5_K_M	5	6.8 GB	High	F0
Q6_K	6	7.7 GB	High	F0
Q8_0	8	10.1 GB	Very High	F0
F16	16	19.3 GB	Maximum	F0

Get started

Copy-paste commands to run Ornith 1.0 9B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "deepreinforce-ai/Ornith-1.0-9B" \
  --hf-file "Ornith-1.0-9B-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Upgrade-Optionen

Hardware, die Ornith 1.0 9B gut ausführt

RTX 3060 12GBGünstige Wahl

12 GB VRAM (+4)360 GB/s (+136)

Raises estimated decode speed by about 127%.44.5 tok/s Dekodierung

Raises estimated decode speed by about 127%.

Adds memory headroom for longer context windows and future model growth.

ca. $329 MSRP

RTX 5060 Ti 16GBBestes Preis-Leistungs-Verhältnis

16 GB VRAM (+8)448 GB/s (+224)

Raises estimated decode speed by about 166%.52.1 tok/s Dekodierung

Raises estimated decode speed by about 166%.

Adds memory headroom for longer context windows and future model growth.

ca. $449 MSRP

RTX 4060 Ti 16GBNVIDIA-Upgrade

16 GB VRAM (+8)288 GB/s (+64)

Raises estimated decode speed by about 101%.39.4 tok/s Dekodierung

Raises estimated decode speed by about 101%.

Adds memory headroom for longer context windows and future model growth.

ca. $499 MSRP

Frequently asked questions

Can RTX 3050 8GB run Ornith 1.0 9B?

Yes, RTX 3050 8GB can run Ornith 1.0 9B at Q5_K_M quantization (Very compromised (needs ~0.9 GB host RAM)). The recommended Q4_K_M requires 9.7 GB which exceeds available memory, but at Q5_K_M it needs only 9.3 GB. Expected decode speed: 13.2 tok/s.

How much VRAM does Ornith 1.0 9B need?

Ornith 1.0 9B (9.399999618530273B parameters) requires approximately 9.7 GB at Q4_K_M quantization. On RTX 3050 8GB, it fits at Q5_K_M using 9.3 GB.

What is the best quantization for Ornith 1.0 9B?

The recommended quantization is Q4_K_M, but on RTX 3050 8GB the best fitting quantization is Q5_K_M, which uses 9.3 GB.

What speed will Ornith 1.0 9B run at on RTX 3050 8GB?

On RTX 3050 8GB, Ornith 1.0 9B achieves approximately 13.2 tokens per second decode speed with a time-to-first-token of 14650ms using Q5_K_M quantization.

Can RTX 3050 8GB run Ornith 1.0 9B for coding?

For coding workloads, Ornith 1.0 9B on RTX 3050 8GB receives a F grade with 12.9 tok/s and 4K context.

What context window can Ornith 1.0 9B use on RTX 3050 8GB?

On RTX 3050 8GB, Ornith 1.0 9B can safely use up to 4K tokens of context at Q5_K_M quantization. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Ornith 1.0 9B feels slow on RTX 3050 8GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for RTX 3050 8GB See all hardware for Ornith 1.0 9B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/ornith-1.0-9b-on-rtx-3050-8gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: