Mac Studio M2 Ultra 128GBコスパ重視
128 GB Unified (+48)
C
This setup is broadly balanced for this model.98 tok/sデコード
〜$3,999 MSRP
Can MD Judge v0 2 internlm2 7b i1 run on NVIDIA H800 80GB?
YES — Runs Great
C45Usable
Estimated from fit model
MD Judge v0 2 internlm2 7b i1 needs ~14.3 GB VRAM. NVIDIA H800 80GB has 80.0 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) — 14.3 GB, 98.0 tok/s, Runs well
14.3 GB required80.0 GB available
18% VRAM used
Fit status
Runs well
Decode
98.0 tok/s
TTFT
1976 ms
Safe context
1.3M
Memory
14.3 GB / 80.0 GB
Memory breakdown
Weights4.3 GB
KV Cache0.8 GB
Runtime1.2 GB
Headroom8.0 GB
See how fast it feels
See how fast it feelsMD Judge v0 2 internlm2 7b i1 on NVIDIA H800 80GB
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: 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 | 1.3M |
| Coding | C | Runs well | 98.0 tok/s | 1976 ms | 1.3M |
| Agentic Coding | C | Runs well | 98.0 tok/s | 2873 ms | 1.3M |
| Reasoning | C | Runs well | 98.0 tok/s | 2335 ms | 1.3M |
| RAG | C | Runs well | 98.0 tok/s | 3592 ms | 1.3M |
Quantization options
How MD Judge v0 2 internlm2 7b i1 (7B params) fits at each quantization level on NVIDIA H800 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | D39 |
Q3_K_S | 3 | 3.4 GB | Low | D39 |
NVFP4 | 4 | 3.9 GB | Medium | D39 |
Q4_K_M | 4 | 4.3 GB | Medium | D39 |
Q5_K_M | 5 | 5.0 GB | High | D39 |
Q6_K | 6 | 5.7 GB | High | D39 |
Q8_0 | 8 | 7.5 GB | Very High | D39 |
F16Best for your GPU | 16 | 14.3 GB | Maximum | C40 |
Get started
Copy-paste commands to run MD Judge v0 2 internlm2 7b i1 on your machine.
Run
lms load hf-mradermacher--md-judge-v0-2-internlm2-7b-i1-gguf && lms server startアップグレードオプション
MD Judge v0 2 internlm2 7b i1を快適に動かすハードウェア
Frequently asked questions
Can NVIDIA H800 80GB run MD Judge v0 2 internlm2 7b i1?
Yes, NVIDIA H800 80GB can run MD Judge v0 2 internlm2 7b i1 with a C grade (Runs well). Expected decode speed: 98.0 tok/s.
How much VRAM does MD Judge v0 2 internlm2 7b i1 need?
MD Judge v0 2 internlm2 7b i1 (7B parameters) requires approximately 14.3 GB of memory with Q4_K_M quantization.
What is the best quantization for MD Judge v0 2 internlm2 7b i1?
The recommended quantization for MD Judge v0 2 internlm2 7b i1 is Q4_K_M, which balances quality and memory efficiency.
What speed will MD Judge v0 2 internlm2 7b i1 run at on NVIDIA H800 80GB?
On NVIDIA H800 80GB, MD Judge v0 2 internlm2 7b i1 achieves approximately 98.0 tokens per second decode speed with a time-to-first-token of 1976ms using Q4_K_M quantization.
Can NVIDIA H800 80GB run MD Judge v0 2 internlm2 7b i1 for coding?
For coding workloads, MD Judge v0 2 internlm2 7b i1 on NVIDIA H800 80GB receives a C grade with 98.0 tok/s and 1.3M context.
What context window can MD Judge v0 2 internlm2 7b i1 use on NVIDIA H800 80GB?
On NVIDIA H800 80GB, MD Judge v0 2 internlm2 7b i1 can safely use up to 1.3M 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-mradermacher--md-judge-v0-2-internlm2-7b-i1-gguf-on-h800-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: