RUNLOCALAIv38
→WILL IT RUNBEST GPUCOMPARETROUBLESHOOTSTARTPULSEMODELSHARDWARETOOLSBENCH
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Quick answers
REF
  • All buyer guides
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
Will it run? / Intel Arc A770 16GB / long context

What can Intel Arc A770 16GB run for long context?

Build: Intel Arc A770 16GB + — + 32 GB RAM (windows)

Memory: 16 GB VRAM + 32 GB system RAM
Runner: llama.cpp (Vulkan)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
41 models

Ranked by fit for long context use case + predicted speed. Click a row for VRAM breakdown.

#1Falcon Mamba 7B
7B
falcon
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 8.4 GBHeadroom: 7.6 GB
60
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#2Codestral Mamba 7B
7B
mistral
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 8.4 GBHeadroom: 7.6 GB
60
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#3Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.1 GBHeadroom: 6.9 GB
ollama run qwen3:8b
52
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#4Ministral 8B Instruct
8B
mistral
Quant: Q4_K_MContext: 2,048VRAM: 9.1 GBHeadroom: 6.9 GB
52
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#5InternLM 2.5 7B Chat
7B
internlm
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 8.4 GBHeadroom: 7.6 GB
60
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#6DeepSeek R1 Distill Qwen 7B
7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 8.4 GBHeadroom: 7.6 GB
ollama run deepseek-r1:7b
60
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#7Qwen 3 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 8.4 GBHeadroom: 7.6 GB
60
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#8Qwen 2.5 Coder 7B Instruct
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 8.4 GBHeadroom: 7.6 GB
ollama run qwen2.5-coder:7b
60
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#9Hermes 3 Llama 3.1 8B
8B
hermes
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.1 GBHeadroom: 6.9 GB
ollama run hermes3:8b
52
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#10Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.1 GBHeadroom: 6.9 GB
52
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#11DeepSeek R1 Distill Llama 8B
8B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.1 GBHeadroom: 6.9 GB
52
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
#12Granite 3.2 8B
8B
granite
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.1 GBHeadroom: 6.9 GB
52
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →

Runs with tradeoffs
68 models

Tight VRAM, partial CPU offload, or context-limited.

Ministral 3B Instruct
3B
mistral
Quant: Q4_K_MContext: 8,192VRAM: 12.6 GBHeadroom: 3.4 GB
  • • Tight VRAM fit — only 3.4 GB headroom left for context growth
139
tok/s
E
Weights
1.81 GB
KV cache
1.50 GB
Activations
8.28 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
Phi-3.5 Mini Instruct
3.8B
phi
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 15.3 GBHeadroom: 0.7 GB
  • • Tight VRAM fit — only 0.7 GB headroom left for context growth
ollama run phi3.5:3.8b
62
tok/s
E
Weights
4.04 GB
KV cache
1.90 GB
Activations
8.39 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
Gemma 4 E4B (Effective 4B)
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 15.7 GBHeadroom: 0.3 GB
  • • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run gemma4:e4b
59
tok/s
E
Weights
4.25 GB
KV cache
2.00 GB
Activations
8.40 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 14.7 GBHeadroom: 1.3 GB
  • • Tight VRAM fit — only 1.3 GB headroom left for context growth
ollama run qwen2.5:7b
52
tok/s
E
Weights
4.81 GB
KV cache
0.47 GB
Activations
8.43 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
Llama 3.1 8B Instruct
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 15.3 GBHeadroom: 0.7 GB
  • • Tight VRAM fit — only 0.7 GB headroom left for context growth
ollama run llama3.1:8b
52
tok/s
E
Weights
4.83 GB
KV cache
1.07 GB
Activations
8.43 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
Nemotron 3 Nano (30B-A3B)
30B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GB
  • • Partial CPU offload: ~38% of layers run on CPU
ollama run nemotron3:nano
14
tok/s
E
Weights
18.11 GB
KV cache
3.75 GB
Activations
2.95 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
Mistral Nemo 12B Instruct
12B
mistral
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 12.2 GBHeadroom: 3.8 GB
  • • Tight VRAM fit — only 3.8 GB headroom left for context growth
ollama run mistral-nemo:12b
35
tok/s
E
Weights
7.25 GB
KV cache
1.50 GB
Activations
2.41 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →
Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 13.7 GBHeadroom: 2.3 GB
  • • Tight VRAM fit — only 2.3 GB headroom left for context growth
ollama run qwen3:14b
30
tok/s
E
Weights
8.45 GB
KV cache
1.75 GB
Activations
2.47 GB
Runtime
1.00 GB
Model details →Run-on benchmark page →

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

+32 GB system RAM

~$80–150

Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 16 new comfortable, 78 new tradeoff

  • • Gemma 3 1B
  • • Llama 3.2 1B Instruct
  • • Whisper Large v3
  • • SmolLM 2 1.7B Instruct
Shop this upgrade↗

Add a second Intel Arc A770 16GB

~$269

Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.

Unlocks: 72 new comfortable

  • • Gemma 3 1B
  • • Llama 3.2 1B Instruct
  • • Gemma 4 E2B (Effective 2B)
  • • Llama 3.2 3B Instruct
Shop this upgrade↗

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)
1600B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

—
Llama 4 Scout
109B
llama
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

—
DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

—

How to read these numbers

M
Measured — we ran this exact combo on owner hardware.

~
Extrapolated — predicted from a measured benchmark on similar-bandwidth hardware.

E
Estimated — pure formula based on VRAM bandwidth and model architecture.

Full methodology →

Want a specific benchmark we don't have? Email support@runlocalai.co and we'll prioritize it.