32 GB VRAM (+8)1792 GB/s (+1492)
B
Raises estimated decode speed by about 100%.98 tok/s decode
Raises estimated decode speed by about 100%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Can Samantha 7B run on NVIDIA L4 24GB?
YES — Runs Great
B65Good
○Estimated from fit model
Samantha 7B needs ~9.8 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~49 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: Balanced
Share:
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) — 9.8 GB, 49.1 tok/s, Runs well
9.8 GB required24.0 GB available
41% VRAM used
Fit status
Runs well
Decode
49.1 tok/s
TTFT
3944 ms
Safe context
4K
Memory
9.8 GB / 24.0 GB
Memory breakdown
Weights4.3 GB
KV Cache2.0 GB
Runtime1.2 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelsSamantha 7B on NVIDIA L4 24GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.
When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.
Key benefits of running locally:
- Full privacy: your prompts never leave your machine
- No per-token cost or rate limits
- Works offline once the model is downloaded
- Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:
Model size Q4 (4-bit) Q8 (8-bit) FP16
7B params ~4.3 GB ~7.5 GB ~14 GB
13B params ~7.9 GB ~13.9 GB ~26 GB
70B params ~42.7 GB ~74.9 GB ~140 GB
Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 49.1 tok/s decode · 3.9s TTFT (warm) · 123 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 | B | Runs well | 49.1 tok/s | 2151 ms | 4K |
| Coding | B | Runs well | 49.1 tok/s | 3944 ms | 4K |
| Agentic Coding | B | Runs well | 49.1 tok/s | 5736 ms | 4K |
| Reasoning | B | Runs well | 49.1 tok/s | 4661 ms | 4K |
| RAG | B | Runs well | 49.1 tok/s | 7170 ms | 4K |
Quantization options
How Samantha 7B (7B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | B60 |
Q3_K_S | 3 | 3.4 GB | Low | B61 |
NVFP4 | 4 | 3.9 GB | Medium | B61 |
Q4_K_M | 4 | 4.3 GB | Medium | B61 |
Q5_K_M | 5 | 5.0 GB | High | B62 |
Q6_K | 6 | 5.7 GB | High | B62 |
Q8_0 | 8 | 7.5 GB | Very High | B63 |
F16Best for your GPU | 16 | 14.3 GB | Maximum | B66 |
Get started
Copy-paste commands to run Samantha 7B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "cognitivecomputations/samantha-1.1-llama-7b" \
--hf-file "samantha-1.1-llama-7b-Q4_K_M.gguf" \
-c 4096 -ngl 99Upgrade options
Hardware that runs Samantha 7B well
32 GB VRAM (+8)896 GB/s (+596)
B
Raises estimated decode speed by about 100%.98 tok/s decode
Raises estimated decode speed by about 100%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
32 GB VRAM (+8)576 GB/s (+276)
B
Raises estimated decode speed by about 100%.98 tok/s decode
Raises estimated decode speed by about 100%.
Adds memory headroom for longer context windows and future model growth.
~$4,000 MSRP