12 GB VRAM (+4)360 GB/s (+88)
A
Adds memory headroom for longer context windows and future model growth.50.2 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$329 MSRP
Can Samantha 7B run on RTX 4060 8GB?
YES — With Offload
B68Good
○Estimated from fit model
Samantha 7B needs ~7.9 GB VRAM. RTX 4060 8GB has 8.0 GB. With Q4_K_M quantization, expect ~46 tok/s.
Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: StandardBottleneck: 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) — 7.9 GB, 46.0 tok/s, Runs with offload
7.9 GB required8.0 GB available
99% VRAM used
Fit status
Runs with offload
Decode
46.0 tok/s
TTFT
4210 ms
Safe context
4K
Memory
7.9 GB / 8.0 GB
Memory breakdown
Weights4.3 GB
KV Cache2.0 GB
Runtime0.9 GB
Headroom0.8 GB
See how fast it feels
See how fast it feelsSamantha 7B on RTX 4060 8GB
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: 46.0 tok/s decode · 4.2s TTFT (warm) · 115 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 | B | Tight fit | 46.0 tok/s | 2296 ms | 4K |
| Coding | B | Runs with offload | 46.0 tok/s | 4210 ms | 4K |
| Agentic Coding | F | Too heavy | 22.4 tok/s | 12581 ms | 4K |
| Reasoning | B | Runs with offload | 46.0 tok/s | 4975 ms | 4K |
| RAG | F | Too heavy | 22.1 tok/s | 15901 ms | 4K |
Quantization options
How Samantha 7B (7B params) fits at each quantization level on RTX 4060 8GB (8.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | B69 |
Q3_K_S | 3 | 3.4 GB | Low | B70 |
NVFP4 | 4 |
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
16 GB VRAM (+8)448 GB/s (+176)
B
Raises estimated decode speed by about 52%.69.9 tok/s decode
Raises estimated decode speed by about 52%.
Adds memory headroom for longer context windows and future model growth.
~$449 MSRP
12 GB VRAM (+4)672 GB/s (+400)
A
Raises estimated decode speed by about 132%.106.6 tok/s decode
Raises estimated decode speed by about 132%.
Adds memory headroom for longer context windows and future model growth.
~$549 MSRP