Can OpenSafetyLab MD Judge v0 2 internlm2 7b run on GTX 1660 Super 6GB?

BARELY — Tight on Memory

D39Poor

Estimated from fit model

OpenSafetyLab MD Judge v0 2 internlm2 7b needs ~6.6 GB VRAM. GTX 1660 Super 6GB has 6.0 GB. With Q4_K_M quantization, expect ~26 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: StandardBottleneck: Host offload

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) — 6.6 GB, 25.7 tok/s, Very compromised (needs ~0.4 GB host RAM)

6.6 GB required6.0 GB available

110% VRAM needed

0.6 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~0.4 GB host RAM)

Decode

25.7 tok/s

TTFT

7536 ms

Safe context

Memory

6.6 GB / 6.0 GB

Offload

10%

Memory breakdown

Weights4.3 GB

KV Cache0.8 GB

Runtime0.9 GB

Headroom0.6 GB

See how fast it feels

See how fast it feelsOpenSafetyLab   MD Judge v0 2 internlm2 7b on GTX 1660 Super 6GB
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: 25.7 tok/s decode · 7.5s TTFT (warm) · 64 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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.

Older PCIe generation

PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 0.4 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs with offload (needs ~0.1 GB host RAM)	29.6 tok/s	3570 ms	4K
Coding	D	Very compromised (needs ~0.4 GB host RAM)	25.7 tok/s	7536 ms	4K
Agentic Coding	F	Too heavy	19.9 tok/s	14183 ms	4K
Reasoning	D	Very compromised (needs ~0.4 GB host RAM)	25.7 tok/s	8906 ms	4K
RAG	F	Too heavy	19.9 tok/s	17729 ms	4K

Quantization options

How OpenSafetyLab MD Judge v0 2 internlm2 7b (7B params) fits at each quantization level on GTX 1660 Super 6GB (6.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	C54
Q3_K_SBest for your GPU	3	3.4 GB	Low	C53
NVFP4	4	3.9 GB	Medium	F0
Q4_K_M	4	4.3 GB	Medium	F0
Q5_K_M	5	5.0 GB	High	F0
Q6_K	6	5.7 GB	High	F0
Q8_0	8	7.5 GB	Very High	F0
F16	16	14.3 GB	Maximum	F0

Get started

Copy-paste commands to run OpenSafetyLab MD Judge v0 2 internlm2 7b on your machine.

Run

lms load hf-richarderkhov--opensafetylab---md-judge-v0-2-internlm2-7b-gguf && lms server start

Opções de upgrade

Hardware que roda bem OpenSafetyLab MD Judge v0 2 internlm2 7b

RTX 3050 8GBOpção econômica

8 GB VRAM (+2)

Removes host-memory offload, which is usually the single biggest latency and throughput win.29.1 tok/s decodificação

Removes host-memory offload, which is usually the single biggest latency and throughput win.

Adds memory headroom for longer context windows and future model growth.

~$249 MSRP

RTX 5060 8GBMelhor custo-benefício

8 GB VRAM (+2)448 GB/s (+112)

Removes host-memory offload, which is usually the single biggest latency and throughput win.64 tok/s decodificação

Removes host-memory offload, which is usually the single biggest latency and throughput win.

Raises estimated decode speed by about 149%.

~$299 MSRP

RTX 5050 8GBUpgrade NVIDIA

8 GB VRAM (+2)

Removes host-memory offload, which is usually the single biggest latency and throughput win.44.1 tok/s decodificação

Removes host-memory offload, which is usually the single biggest latency and throughput win.

Raises estimated decode speed by about 72%.

~$299 MSRP

Frequently asked questions

Can GTX 1660 Super 6GB run OpenSafetyLab MD Judge v0 2 internlm2 7b?

Yes, GTX 1660 Super 6GB can run OpenSafetyLab MD Judge v0 2 internlm2 7b with a D grade (Very compromised (needs ~0.4 GB host RAM)). Expected decode speed: 25.7 tok/s.

How much VRAM does OpenSafetyLab MD Judge v0 2 internlm2 7b need?

OpenSafetyLab MD Judge v0 2 internlm2 7b (7B parameters) requires approximately 6.6 GB of memory with Q4_K_M quantization.

What is the best quantization for OpenSafetyLab MD Judge v0 2 internlm2 7b?

The recommended quantization for OpenSafetyLab MD Judge v0 2 internlm2 7b is Q4_K_M, which balances quality and memory efficiency.

What speed will OpenSafetyLab MD Judge v0 2 internlm2 7b run at on GTX 1660 Super 6GB?

On GTX 1660 Super 6GB, OpenSafetyLab MD Judge v0 2 internlm2 7b achieves approximately 25.7 tokens per second decode speed with a time-to-first-token of 7536ms using Q4_K_M quantization.

Can GTX 1660 Super 6GB run OpenSafetyLab MD Judge v0 2 internlm2 7b for coding?

For coding workloads, OpenSafetyLab MD Judge v0 2 internlm2 7b on GTX 1660 Super 6GB receives a D grade with 25.7 tok/s and 4K context.

What context window can OpenSafetyLab MD Judge v0 2 internlm2 7b use on GTX 1660 Super 6GB?

On GTX 1660 Super 6GB, OpenSafetyLab MD Judge v0 2 internlm2 7b can safely use up to 4K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if OpenSafetyLab MD Judge v0 2 internlm2 7b feels slow on GTX 1660 Super 6GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for GTX 1660 Super 6GB See all hardware for OpenSafetyLab MD Judge v0 2 internlm2 7b

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-richarderkhov--opensafetylab---md-judge-v0-2-internlm2-7b-gguf-on-gtx-1660-super-6gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: