Mac Studio M3 Ultra 256GB经济之选
256 GB Unified (+115)
C
Adds memory headroom for longer context windows and future model growth.98 tok/s 解码
Adds memory headroom for longer context windows and future model growth.
~$6,999 MSRP
Can Mamba Codestral 7B v0.1 run on NVIDIA H200 PCIe 141GB?
YES — Runs Great
C45Usable
Estimated from fit model
Mamba Codestral 7B v0.1 needs ~20.4 GB VRAM. NVIDIA H200 PCIe 141GB has 141.0 GB. With Q4_K_M quantization, expect ~98 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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.
Select quantization to explore
Q4_K_M (Medium quality) — 20.4 GB, 98.0 tok/s, Runs well
20.4 GB required141.0 GB available
14% VRAM used
Fit status
Runs well
Decode
98.0 tok/s
TTFT
1976 ms
Safe context
2.4M
Memory
20.4 GB / 141.0 GB
Memory breakdown
Weights4.3 GB
KV Cache0.8 GB
Runtime1.2 GB
Headroom14.1 GB
See how fast it feels
See how fast it feelsMamba Codestral 7B v0.1 on NVIDIA H200 PCIe 141GB
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: 98.0 tok/s decode · 2.0s TTFT (warm) · 245 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 | C | Runs well | 98.0 tok/s | 1078 ms | 2.4M |
| Coding | C | Runs well | 98.0 tok/s | 1976 ms | 2.4M |
| Agentic Coding | C | Runs well | 98.0 tok/s | 2873 ms | 2.4M |
| Reasoning | C | Runs well | 98.0 tok/s | 2335 ms | 2.4M |
| RAG | C | Runs well | 98.0 tok/s | 3592 ms | 2.4M |
Inference speed
Mamba Codestral 7B v0.1 inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Mamba Codestral 7B v0.1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~98 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 | 98.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 98.0 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 98.0 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 98.0 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 98.0 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 98.0 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 98.0 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 98.0 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 92.6 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 92.6 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 88.5 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 64.6 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 59.3 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 56.6 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 55.6 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 53.5 | Tight |
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 Mamba Codestral 7B v0.1 (7B params) fits at each quantization level on NVIDIA H200 PCIe 141GB (141.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | D38 |
Q3_K_S | 3 | 3.4 GB | Low | D37 |
NVFP4 | 4 | 3.9 GB | Medium | D37 |
Q4_K_M | 4 | 4.3 GB | Medium | D37 |
Q5_K_M | 5 | 5.0 GB | High | D37 |
Q6_K | 6 | 5.7 GB | High | D38 |
Q8_0 | 8 | 7.5 GB | Very High | D38 |
F16Best for your GPU | 16 | 14.3 GB | Maximum | D38 |
Get started
Copy-paste commands to run Mamba Codestral 7B v0.1 on your machine.
Run
lms load hf-gabriellarson--mamba-codestral-7b-v0-1-gguf && lms server start升级选项
能流畅运行 Mamba Codestral 7B v0.1 的硬件
Frequently asked questions
Can NVIDIA H200 PCIe 141GB run Mamba Codestral 7B v0.1?
Yes, NVIDIA H200 PCIe 141GB can run Mamba Codestral 7B v0.1 with a C grade (Runs well). Expected decode speed: 98.0 tok/s.
How much VRAM does Mamba Codestral 7B v0.1 need?
Mamba Codestral 7B v0.1 (7B parameters) requires approximately 20.4 GB of memory with Q4_K_M quantization.
What is the best quantization for Mamba Codestral 7B v0.1?
The recommended quantization for Mamba Codestral 7B v0.1 is Q4_K_M, which balances quality and memory efficiency.
What speed will Mamba Codestral 7B v0.1 run at on NVIDIA H200 PCIe 141GB?
On NVIDIA H200 PCIe 141GB, Mamba Codestral 7B v0.1 achieves approximately 98.0 tokens per second decode speed with a time-to-first-token of 1976ms using Q4_K_M quantization.
Can NVIDIA H200 PCIe 141GB run Mamba Codestral 7B v0.1 for coding?
For coding workloads, Mamba Codestral 7B v0.1 on NVIDIA H200 PCIe 141GB receives a C grade with 98.0 tok/s and 2.4M context.
What context window can Mamba Codestral 7B v0.1 use on NVIDIA H200 PCIe 141GB?
On NVIDIA H200 PCIe 141GB, Mamba Codestral 7B v0.1 can safely use up to 2.4M tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-gabriellarson--mamba-codestral-7b-v0-1-gguf-on-h200-pcie-141gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: