Can Leanstral 119B A6B run on AMD Instinct MI350X 288GB?

YES — Runs Great

S86Excellent

Estimated from fit model

Leanstral 119B A6B needs ~112.6 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~178 tok/s.

Runtime: vLLMCapacity: RoomyBandwidth: HighStack: OptimizedBottleneck: 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) — 112.6 GB, 177.9 tok/s, Runs well

112.6 GB required288.0 GB available

39% VRAM used

Fit status

Runs well

Decode

177.9 tok/s

TTFT

1088 ms

Safe context

256K

Memory

112.6 GB / 288.0 GB

Memory breakdown

Weights72.6 GB

KV Cache8.8 GB

Runtime2.4 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsLeanstral 119B A6B on AMD Instinct MI350X 288GB
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: 177.9 tok/s decode · 1.1s TTFT (warm) · 445 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	S	Runs well	177.9 tok/s	594 ms	256K
Coding	S	Runs well	177.9 tok/s	1088 ms	256K
Agentic Coding	S	Runs well	177.9 tok/s	1583 ms	256K
Reasoning	S	Runs well	177.9 tok/s	1286 ms	256K
RAG	S	Runs well	177.9 tok/s	1979 ms	256K

Inference speed

Leanstral 119B A6B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Leanstral 119B A6B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~17 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?
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	17.0	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	11.9	Too big
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	11.3	Too big
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	8.8	Too big
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	7.4	Too big
2× RTX 4090 24GB	48 GB	Q4_K_M	6.7	Too big
2× RTX 3090 24GB	48 GB	Q4_K_M	5.8	Too big
RTX 5090 32GB	32 GB	Q4_K_M	5.5	Too big
4× RTX 3060 12GB	48 GB	Q4_K_M	5.1	Too big
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	3.7	Too big
RTX 4090 24GB	24 GB	Q4_K_M	3.5	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	3.2	Too big
RTX 3090 24GB	24 GB	Q4_K_M	3.0	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	2.8	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	2.6	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	2.4	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	2.0	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 Leanstral 119B A6B (119B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	A75
Q3_K_S	3	58.3 GB	Low	A76
NVFP4	4	66.6 GB	Medium	A76
Q4_K_M	4	72.6 GB	Medium	A77
Q5_K_M	5	85.7 GB	High	A78
Q6_K	6	97.6 GB	High	A79
Q8_0	8	127.3 GB	Very High	A81
F16Best for your GPU	16	244.0 GB	Maximum	A84

Get started

Copy-paste commands to run Leanstral 119B A6B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "mistralai/Leanstral-2603" \
  --hf-file "Leanstral-2603-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	67.7 tok/s
Qwen 3.5 122B A10B	122B	S	178.4 tok/s
DeepSeek V4 Flash	284B	S	95.6 tok/s
Pixtral Large 124B	124B	S	67.2 tok/s
Qwen 3 235B A22B	235B	S	90.3 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run Leanstral 119B A6B?

Yes, AMD Instinct MI350X 288GB can run Leanstral 119B A6B with a S grade (Runs well). Expected decode speed: 177.9 tok/s.

How much VRAM does Leanstral 119B A6B need?

Leanstral 119B A6B (119B parameters) requires approximately 112.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Leanstral 119B A6B?

The recommended quantization for Leanstral 119B A6B is Q4_K_M, which balances quality and memory efficiency.

What speed will Leanstral 119B A6B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Leanstral 119B A6B achieves approximately 177.9 tokens per second decode speed with a time-to-first-token of 1088ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Leanstral 119B A6B for coding?

For coding workloads, Leanstral 119B A6B on AMD Instinct MI350X 288GB receives a S grade with 177.9 tok/s and 256K context.

What context window can Leanstral 119B A6B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Leanstral 119B A6B can safely use up to 256K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for Leanstral 119B A6B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/leanstral-119b-a6b-on-instinct-mi350x-288gb" 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

177.9 tok/s

594 ms

256K

Coding

Runs well

177.9 tok/s

1088 ms

256K

Agentic Coding

Runs well

177.9 tok/s

1583 ms

256K

Reasoning

Runs well

177.9 tok/s

1286 ms

256K

RAG

Runs well

177.9 tok/s

1979 ms

256K

Leanstral 119B A6B inference speed — tokens per second by GPU & Mac

GPU / Mac

Memory

Quant

Speed (tok/s)

Fits?

Mac Studio M3 Ultra 256GB

256 GB

Q4_K_M

17.0

Fits

Mac Studio M2 Ultra 128GB

128 GB

Q4_K_M

11.9

Too big

Mac Studio M1 Ultra 128GB

128 GB

Q4_K_M

11.3

Too big

MacBook Pro M4 Max 128GB

128 GB

Q4_K_M

8.8

Too big

2× RX 7900 XTX 24GB

48 GB

Q4_K_M

7.4

Too big

2× RTX 4090 24GB

48 GB

Q4_K_M

6.7

Too big

2× RTX 3090 24GB

48 GB

Q4_K_M

5.8

Too big

RTX 5090 32GB

32 GB

Q4_K_M

5.5

Too big

4× RTX 3060 12GB

48 GB

Q4_K_M

5.1

Too big

MacBook Pro M4 Max 64GB

64 GB

Q4_K_M

3.7

Too big

RTX 4090 24GB

24 GB

Q4_K_M

3.5

Too big

RX 7900 XTX 24GB

24 GB

Q4_K_M

3.2

Too big

RTX 3090 24GB

24 GB

Q4_K_M

3.0

Too big

RTX 4080 Super 16GB

16 GB

Q4_K_M

2.8

Too big

MacBook Pro M3 Max 64GB

64 GB

Q4_K_M

2.6

Too big

MacBook Pro M1 Max 64GB

64 GB

Q4_K_M

2.4

Too big

RTX 4070 12GB

12 GB

Q4_K_M

2.0

Too big

RTX 3060 12GB

12 GB

Q4_K_M

2.0

Too big

RTX 4060 8GB

8 GB

Q4_K_M

2.0

Too big

MacBook Pro M4 Pro 48GB

48 GB

Q4_K_M

2.0

Too big

Quantization options

How Leanstral 119B A6B (119B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	A75
Q3_K_S	3	58.3 GB	Low	A76
NVFP4	4	66.6 GB	Medium	A76
Q4_K_M	4	72.6 GB	Medium	A77
Q5_K_M	5	85.7 GB	High	A78
Q6_K	6	97.6 GB	High	A79
Q8_0	8	127.3 GB	Very High	A81
F16Best for your GPU	16	244.0 GB	Maximum	A84

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

67.7 tok/s

Qwen 3.5 122B A10B

122B

178.4 tok/s

DeepSeek V4 Flash

284B

95.6 tok/s

Pixtral Large 124B

124B

67.2 tok/s

Qwen 3 235B A22B

235B

90.3 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run Leanstral 119B A6B?

Yes, AMD Instinct MI350X 288GB can run Leanstral 119B A6B with a S grade (Runs well). Expected decode speed: 177.9 tok/s.

How much VRAM does Leanstral 119B A6B need?

Leanstral 119B A6B (119B parameters) requires approximately 112.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Leanstral 119B A6B?

The recommended quantization for Leanstral 119B A6B is Q4_K_M, which balances quality and memory efficiency.

What speed will Leanstral 119B A6B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Leanstral 119B A6B achieves approximately 177.9 tokens per second decode speed with a time-to-first-token of 1088ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Leanstral 119B A6B for coding?

For coding workloads, Leanstral 119B A6B on AMD Instinct MI350X 288GB receives a S grade with 177.9 tok/s and 256K context.

What context window can Leanstral 119B A6B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Leanstral 119B A6B can safely use up to 256K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.