Can Ornith 1.0 35B A3B run on AMD Instinct MI250 128GB?

YES — Runs Great

A78Great

Estimated from fit model

Ornith 1.0 35B A3B needs ~35.4 GB VRAM. AMD Instinct MI250 128GB has 128.0 GB. With Q4_K_M quantization, expect ~300 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 35.4 GB, 300.0 tok/s, Runs well

35.4 GB required128.0 GB available

28% VRAM used

Fit status

Runs well

Decode

300.0 tok/s

TTFT

645 ms

Safe context

262K

Memory

35.4 GB / 128.0 GB

Memory breakdown

Weights21.4 GB

KV Cache0.3 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsOrnith 1.0 35B A3B on AMD Instinct MI250 128GB
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: 300.0 tok/s decode · 645ms TTFT (warm) · 750 tok/s prefill

What limits this setup

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.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	300.0 tok/s	352 ms	262K
Coding	A	Runs well	300.0 tok/s	645 ms	262K
Agentic Coding	A	Runs well	300.0 tok/s	939 ms	262K
Reasoning	A	Runs well	300.0 tok/s	763 ms	262K
RAG	A	Runs well	300.0 tok/s	1173 ms	262K

Inference speed

Ornith 1.0 35B A3B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Ornith 1.0 35B A3B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~139 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	139.1	Fits
RTX 4090 24GB	24 GB	Q4_K_M	77.7	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	76.8	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	65.5	Offloads
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	64.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	62.1	Offloads
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	60.7	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	47.4	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	47.4	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	36.4	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	33.4	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	31.9	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	28.3	Too big
RTX 4070 12GB	12 GB	Q4_K_M	9.9	Too big
RTX 3060 12GB	12 GB	Q4_K_M	5.8	Too big
RTX 4060 8GB	8 GB	Q4_K_M	4.4	Too big

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 35B A3B (35.099998474121094B params) fits at each quantization level on AMD Instinct MI250 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	B69
Q3_K_S	3	17.2 GB	Low	B69
NVFP4	4	19.7 GB	Medium	B70
Q4_K_M	4	21.4 GB	Medium	B70
Q5_K_M	5	25.3 GB	High	A70
Q6_K	6	28.8 GB	High	A71
Q8_0	8	37.6 GB	Very High	A72
F16Best for your GPU	16	72.0 GB	Maximum	A78

Get started

Copy-paste commands to run Ornith 1.0 35B A3B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "deepreinforce-ai/Ornith-1.0-35B" \
  --hf-file "Ornith-1.0-35B-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your AMD Instinct MI250 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	31.5 tok/s
Qwen 3.5 122B A10B	122B	S	87.5 tok/s
Mistral Small 4 119B	119B	S	94.8 tok/s
GPT-OSS 120B	117B	S	33.2 tok/s
Command A 111B	111B	S	35.1 tok/s

Frequently asked questions

Can AMD Instinct MI250 128GB run Ornith 1.0 35B A3B?

Yes, AMD Instinct MI250 128GB can run Ornith 1.0 35B A3B with a A grade (Runs well). Expected decode speed: 300.0 tok/s.

How much VRAM does Ornith 1.0 35B A3B need?

Ornith 1.0 35B A3B (35.099998474121094B parameters) requires approximately 35.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Ornith 1.0 35B A3B?

The recommended quantization for Ornith 1.0 35B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Ornith 1.0 35B A3B run at on AMD Instinct MI250 128GB?

On AMD Instinct MI250 128GB, Ornith 1.0 35B A3B achieves approximately 300.0 tokens per second decode speed with a time-to-first-token of 645ms using Q4_K_M quantization.

Can AMD Instinct MI250 128GB run Ornith 1.0 35B A3B for coding?

For coding workloads, Ornith 1.0 35B A3B on AMD Instinct MI250 128GB receives a A grade with 300.0 tok/s and 262K context.

What context window can Ornith 1.0 35B A3B use on AMD Instinct MI250 128GB?

On AMD Instinct MI250 128GB, Ornith 1.0 35B A3B can safely use up to 262K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI250 128GB See all hardware for Ornith 1.0 35B A3B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/ornith-1.0-35b-a3b-on-instinct-mi250-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

300.0 tok/s

352 ms

262K

Coding

Runs well

300.0 tok/s

645 ms

262K

Agentic Coding

Runs well

300.0 tok/s

939 ms

262K

Reasoning

Runs well

300.0 tok/s

763 ms

262K

RAG

Runs well

300.0 tok/s

1173 ms

262K

Ornith 1.0 35B A3B inference speed — tokens per second by GPU & Mac

GPU / Mac

Memory

Quant

Speed (tok/s)

Fits?

RTX 5090 32GB

32 GB

Q4_K_M

139.1

Fits

RTX 4090 24GB

24 GB

Q4_K_M

77.7

Offloads

Mac Studio M3 Ultra 256GB

256 GB

Q4_K_M

76.8

Fits

RX 7900 XTX 24GB

24 GB

Q4_K_M

65.5

Offloads

Mac Studio M2 Ultra 128GB

128 GB

Q4_K_M

64.0

Fits

RTX 3090 24GB

24 GB

Q4_K_M

62.1

Offloads

Mac Studio M1 Ultra 128GB

128 GB

Q4_K_M

60.7

Fits

MacBook Pro M4 Max 128GB

128 GB

Q4_K_M

47.4

Fits

MacBook Pro M4 Max 64GB

64 GB

Q4_K_M

47.4

Fits

MacBook Pro M3 Max 64GB

64 GB

Q4_K_M

36.4

Fits

MacBook Pro M1 Max 64GB

64 GB

Q4_K_M

33.4

Fits

MacBook Pro M4 Pro 48GB

48 GB

Q4_K_M

31.9

Fits

RTX 4080 Super 16GB

16 GB

Q4_K_M

28.3

Too big

RTX 4070 12GB

12 GB

Q4_K_M

9.9

Too big

RTX 3060 12GB

12 GB

Q4_K_M

5.8

Too big

RTX 4060 8GB

8 GB

Q4_K_M

4.4

Too big

Quantization options

How Ornith 1.0 35B A3B (35.099998474121094B params) fits at each quantization level on AMD Instinct MI250 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	B69
Q3_K_S	3	17.2 GB	Low	B69
NVFP4	4	19.7 GB	Medium	B70
Q4_K_M	4	21.4 GB	Medium	B70
Q5_K_M	5	25.3 GB	High	A70
Q6_K	6	28.8 GB	High	A71
Q8_0	8	37.6 GB	Very High	A72
F16Best for your GPU	16	72.0 GB	Maximum	A78

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

31.5 tok/s

Qwen 3.5 122B A10B

122B

87.5 tok/s

Mistral Small 4 119B

119B

94.8 tok/s

GPT-OSS 120B

117B

33.2 tok/s

Command A 111B

111B

35.1 tok/s

Frequently asked questions

Can AMD Instinct MI250 128GB run Ornith 1.0 35B A3B?

Yes, AMD Instinct MI250 128GB can run Ornith 1.0 35B A3B with a A grade (Runs well). Expected decode speed: 300.0 tok/s.

How much VRAM does Ornith 1.0 35B A3B need?

Ornith 1.0 35B A3B (35.099998474121094B parameters) requires approximately 35.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Ornith 1.0 35B A3B?

The recommended quantization for Ornith 1.0 35B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Ornith 1.0 35B A3B run at on AMD Instinct MI250 128GB?

On AMD Instinct MI250 128GB, Ornith 1.0 35B A3B achieves approximately 300.0 tokens per second decode speed with a time-to-first-token of 645ms using Q4_K_M quantization.

Can AMD Instinct MI250 128GB run Ornith 1.0 35B A3B for coding?

For coding workloads, Ornith 1.0 35B A3B on AMD Instinct MI250 128GB receives a A grade with 300.0 tok/s and 262K context.

What context window can Ornith 1.0 35B A3B use on AMD Instinct MI250 128GB?

On AMD Instinct MI250 128GB, Ornith 1.0 35B A3B can safely use up to 262K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.