Mac Studio M3 Ultra 256GBコスパ重視
256 GB Unified (+160)
C
Adds memory headroom for longer context windows and future model growth.109.2 tok/sデコード
Adds memory headroom for longer context windows and future model growth.
〜$6,999 MSRP
Can EXAONE 3.5 7.8B Instruct run on RTX PRO 6000 Blackwell Workstation Edition 96GB?
YES — Runs Great
C45Usable
Estimated from fit model
EXAONE 3.5 7.8B Instruct needs ~16.5 GB VRAM. RTX PRO 6000 Blackwell Workstation Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~109 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) — 16.5 GB, 109.2 tok/s, Runs well
16.5 GB required96.0 GB available
17% VRAM used
Fit status
Runs well
Decode
109.2 tok/s
TTFT
1773 ms
Safe context
1.4M
Memory
16.5 GB / 96.0 GB
Memory breakdown
Weights4.8 GB
KV Cache0.9 GB
Runtime1.2 GB
Headroom9.6 GB
See how fast it feels
See how fast it feelsEXAONE 3.5 7.8B Instruct on RTX PRO 6000 Blackwell Workstation Edition 96GB
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: 109.2 tok/s decode · 1.8s TTFT (warm) · 273 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 | 109.2 tok/s | 967 ms | 1.4M |
| Coding | C | Runs well | 109.2 tok/s | 1773 ms | 1.4M |
| Agentic Coding | C | Runs well | 109.2 tok/s | 2579 ms | 1.4M |
| Reasoning | C | Runs well | 109.2 tok/s | 2095 ms | 1.4M |
| RAG | C | Runs well | 109.2 tok/s | 3223 ms | 1.4M |
Inference speed
EXAONE 3.5 7.8B Instruct inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for EXAONE 3.5 7.8B Instruct at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~109 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 | 109.2 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 109.2 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 109.2 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 109.2 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 109.2 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 109.2 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 97.5 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 92.5 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 79.4 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 78.8 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 78.8 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 50.4 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 49.9 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 46.2 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 41.7 | Offloads |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 40.6 | Fits |
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 EXAONE 3.5 7.8B Instruct (7.800000190734863B params) fits at each quantization level on RTX PRO 6000 Blackwell Workstation Edition 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.0 GB | Low | D39 |
Q3_K_S | 3 | 3.8 GB | Low | D39 |
NVFP4 | 4 | 4.4 GB | Medium | D39 |
Q4_K_M | 4 | 4.8 GB | Medium | D39 |
Q5_K_M | 5 | 5.6 GB | High | D39 |
Q6_K | 6 | 6.4 GB | High | D39 |
Q8_0 | 8 | 8.3 GB | Very High | D39 |
F16Best for your GPU | 16 | 16.0 GB | Maximum | D40 |
Get started
Copy-paste commands to run EXAONE 3.5 7.8B Instruct on your machine.
Run
lms load hf-lgai-exaone--exaone-3-5-7-8b-instruct-gguf && lms server startアップグレードオプション
EXAONE 3.5 7.8B Instructを快適に動かすハードウェア
Frequently asked questions
Can RTX PRO 6000 Blackwell Workstation Edition 96GB run EXAONE 3.5 7.8B Instruct?
Yes, RTX PRO 6000 Blackwell Workstation Edition 96GB can run EXAONE 3.5 7.8B Instruct with a C grade (Runs well). Expected decode speed: 109.2 tok/s.
How much VRAM does EXAONE 3.5 7.8B Instruct need?
EXAONE 3.5 7.8B Instruct (7.800000190734863B parameters) requires approximately 16.5 GB of memory with Q4_K_M quantization.
What is the best quantization for EXAONE 3.5 7.8B Instruct?
The recommended quantization for EXAONE 3.5 7.8B Instruct is Q4_K_M, which balances quality and memory efficiency.
What speed will EXAONE 3.5 7.8B Instruct run at on RTX PRO 6000 Blackwell Workstation Edition 96GB?
On RTX PRO 6000 Blackwell Workstation Edition 96GB, EXAONE 3.5 7.8B Instruct achieves approximately 109.2 tokens per second decode speed with a time-to-first-token of 1773ms using Q4_K_M quantization.
Can RTX PRO 6000 Blackwell Workstation Edition 96GB run EXAONE 3.5 7.8B Instruct for coding?
For coding workloads, EXAONE 3.5 7.8B Instruct on RTX PRO 6000 Blackwell Workstation Edition 96GB receives a C grade with 109.2 tok/s and 1.4M context.
What context window can EXAONE 3.5 7.8B Instruct use on RTX PRO 6000 Blackwell Workstation Edition 96GB?
On RTX PRO 6000 Blackwell Workstation Edition 96GB, EXAONE 3.5 7.8B Instruct can safely use up to 1.4M 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-lgai-exaone--exaone-3-5-7-8b-instruct-gguf-on-rtx-pro-6000-blackwell-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: