RTX 3090 24GB经济之选24 GB VRAM (+8)936 GB/s (+264)
C
Raises estimated decode speed by about 76%.56.5 tok/s 解码
Raises estimated decode speed by about 76%.
Adds memory headroom for longer context windows and future model growth.
~$1,499 MSRP
Can Codestral RAG 19B Pruned i1 run on RTX 4070 Ti Super 16GB?
YES — With Offload
C50Usable
Estimated from fit model
Codestral RAG 19B Pruned i1 needs ~16.6 GB VRAM. RTX 4070 Ti Super 16GB has 16.0 GB. With Q4_K_M quantization, expect ~32 tok/s.
Runtime: OllamaCapacity: OffloadBandwidth: MediumStack: 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) — 16.6 GB, 32.1 tok/s, Runs with offload (needs ~0.4 GB host RAM)
16.6 GB required16.0 GB available
104% VRAM needed
0.6 GB over capacity — needs offload or smaller quantization
Fit status
Runs with offload (needs ~0.4 GB host RAM)
Decode
32.1 tok/s
TTFT
6026 ms
Safe context
12K
Memory
16.6 GB / 16.0 GB
Memory breakdown
Weights11.6 GB
KV Cache2.2 GB
Runtime1.2 GB
Headroom1.6 GB
See how fast it feels
See how fast it feelsCodestral RAG 19B Pruned i1 on RTX 4070 Ti Super 16GB
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: 32.1 tok/s decode · 6.0s TTFT (warm) · 80 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
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
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs with offload | 46.4 tok/s | 2277 ms | 12K |
| Coding | C | Runs with offload (needs ~0.4 GB host RAM) | 32.1 tok/s | 6026 ms | 12K |
| Agentic Coding | D | Very compromised (needs ~1.7 GB host RAM) | 24.7 tok/s | 11421 ms | 12K |
| Reasoning | C | Runs with offload (needs ~0.4 GB host RAM) | 32.1 tok/s | 7122 ms | 12K |
| RAG | D | Very compromised (needs ~1.7 GB host RAM) | 24.7 tok/s | 14277 ms | 12K |
Inference speed
Codestral RAG 19B Pruned i1 inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Codestral RAG 19B Pruned i1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~104 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 | 103.6 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 66.1 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 59.6 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 56.5 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 48.1 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 40.0 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 38.0 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 36.5 | Offloads |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 36.0 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 36.0 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 22.7 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 20.7 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 19.0 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 13.0 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 8.2 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 3.1 | 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 Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on RTX 4070 Ti Super 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.4 GB | Low | C51 |
Q3_K_S | 3 | 9.3 GB | Low | C51 |
NVFP4 | 4 | 10.6 GB | Medium | C50 |
Q4_K_MBest for your GPU | 4 | 11.6 GB | Medium | C50 |
Q5_K_M | 5 | 13.7 GB | High | F0 |
Q6_K | 6 | 15.6 GB | High | F0 |
Q8_0 | 8 | 20.3 GB | Very High | F0 |
F16 | 16 | 38.9 GB | Maximum | F0 |
Get started
Copy-paste commands to run Codestral RAG 19B Pruned i1 on your machine.
Run
lms load hf-mradermacher--codestral-rag-19b-pruned-i1-gguf && lms server start升级选项
能流畅运行 Codestral RAG 19B Pruned i1 的硬件
RTX 3090 24GB经济之选RTX 4090 24GB最佳性价比24 GB VRAM (+8)1008 GB/s (+336)
B
Raises estimated decode speed by about 106%.66.1 tok/s 解码
Raises estimated decode speed by about 106%.
Adds memory headroom for longer context windows and future model growth.
~$1,599 MSRP
RTX PRO 4000 Blackwell 24GBNVIDIA 升级24 GB VRAM (+8)
C
Raises estimated decode speed by about 52%.48.7 tok/s 解码
Raises estimated decode speed by about 52%.
Adds memory headroom for longer context windows and future model growth.
~$1,599 MSRP
Frequently asked questions
Can RTX 4070 Ti Super 16GB run Codestral RAG 19B Pruned i1?
Yes, RTX 4070 Ti Super 16GB can run Codestral RAG 19B Pruned i1 with a C grade (Runs with offload (needs ~0.4 GB host RAM)). Expected decode speed: 32.1 tok/s.
How much VRAM does Codestral RAG 19B Pruned i1 need?
Codestral RAG 19B Pruned i1 (19B parameters) requires approximately 16.6 GB of memory with Q4_K_M quantization.
What is the best quantization for Codestral RAG 19B Pruned i1?
The recommended quantization for Codestral RAG 19B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.
What speed will Codestral RAG 19B Pruned i1 run at on RTX 4070 Ti Super 16GB?
On RTX 4070 Ti Super 16GB, Codestral RAG 19B Pruned i1 achieves approximately 32.1 tokens per second decode speed with a time-to-first-token of 6026ms using Q4_K_M quantization.
Can RTX 4070 Ti Super 16GB run Codestral RAG 19B Pruned i1 for coding?
For coding workloads, Codestral RAG 19B Pruned i1 on RTX 4070 Ti Super 16GB receives a C grade with 32.1 tok/s and 12K context.
What context window can Codestral RAG 19B Pruned i1 use on RTX 4070 Ti Super 16GB?
On RTX 4070 Ti Super 16GB, Codestral RAG 19B Pruned i1 can safely use up to 12K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
What should I upgrade first if Codestral RAG 19B Pruned i1 feels slow on RTX 4070 Ti Super 16GB?
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-mradermacher--codestral-rag-19b-pruned-i1-gguf-on-rtx-4070-ti-super-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: