What can Intel Arc A770 16GB run for reasoning?

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

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

Runs comfortably
59 models

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

#1DeepSeek R1 Distill Qwen 7B
7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.4 GBHeadroom: 6.6 GB
ollama run deepseek-r1:7b
43
tok/s
Estimated
Weights
4.70 GB
KV cache
3.50 GB
Activations
0.24 GB
Runtime
1.00 GB
#2Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 5.8 GB
37
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.00 GB
#3RefinedNeuro RN TR R1
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 5.8 GB
ollama run RefinedNeuro/RN_TR_R1:latest
37
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.00 GB
#4DeepSeek R1 Distill Llama 8B
8B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GB
37
tok/s
Estimated
Weights
4.70 GB
KV cache
4.00 GB
Activations
0.24 GB
Runtime
1.00 GB
#5Phi-4 Reasoning 14B
14B
phi
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 11.6 GBHeadroom: 4.4 GB
ollama run phi4-reasoning:14b
21
tok/s
Estimated
Weights
8.40 GB
KV cache
1.75 GB
Activations
0.42 GB
Runtime
1.00 GB
#6DeepSeek R1 Distill Qwen 14B
14B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 11.6 GBHeadroom: 4.4 GB
ollama run deepseek-r1:14b
21
tok/s
Estimated
Weights
8.40 GB
KV cache
1.75 GB
Activations
0.42 GB
Runtime
1.00 GB
#7Qwen 3 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.1 GBHeadroom: 6.9 GB
43
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
1.00 GB
#8Qwen 2.5 Math 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 7.4 GBHeadroom: 8.6 GB
43
tok/s
Estimated
Weights
4.40 GB
KV cache
1.75 GB
Activations
0.22 GB
Runtime
1.00 GB
#9InternLM 2.5 7B Chat
7B
internlm
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.1 GBHeadroom: 6.9 GB
43
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
1.00 GB
#10Phi-4 14B
14B
phi
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 11.6 GBHeadroom: 4.4 GB
ollama run phi4:14b
21
tok/s
Estimated
Weights
8.40 GB
KV cache
1.75 GB
Activations
0.42 GB
Runtime
1.00 GB
#11RefinedNeuro RN TR R2
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 5.8 GB
ollama run RefinedNeuro/RN_TR_R2:latest
37
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.00 GB
#12Nemotron 3 Nano 9B
9B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 4.9 GB
33
tok/s
Estimated
Weights
5.30 GB
KV cache
4.50 GB
Activations
0.27 GB
Runtime
1.00 GB

Runs with tradeoffs
51 models

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

DeepSeek V3 Lite (16B MoE)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 13.0 GBHeadroom: 3.0 GB
  • • Tight VRAM fit — only 3.0 GB headroom left for context growth
124
tok/s
Estimated
Weights
9.50 GB
KV cache
2.00 GB
Activations
0.48 GB
Runtime
1.00 GB
DeepSeek R1 Distill Mistral 24B
24B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 27.7 GBHeadroom: 7.5 GB
  • • Partial CPU offload: ~42% of layers run on CPU
12
tok/s
Estimated
Weights
14.00 GB
KV cache
12.00 GB
Activations
0.71 GB
Runtime
1.00 GB
Quant: Q4_K_MContext: 8,192VRAM: 34.5 GBHeadroom: 0.7 GB
  • • Partial CPU offload: ~54% of layers run on CPU
10
tok/s
Estimated
Weights
17.10 GB
KV cache
15.50 GB
Activations
0.86 GB
Runtime
1.00 GB
DeepSeek R1 Distill Qwen 32B
32B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 25.0 GBHeadroom: 10.2 GB
  • • Partial CPU offload: ~36% of layers run on CPU
ollama run deepseek-r1:32b
9
tok/s
Estimated
Weights
19.00 GB
KV cache
4.00 GB
Activations
0.95 GB
Runtime
1.00 GB
QwQ 32B Preview
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 25.0 GBHeadroom: 10.2 GB
  • • Partial CPU offload: ~36% of layers run on CPU
ollama run qwq:32b
9
tok/s
Estimated
Weights
19.00 GB
KV cache
4.00 GB
Activations
0.95 GB
Runtime
1.00 GB
DeepSeek R1 Distill Qwen 3 32B
32B
deepseek
Commercial OK
Quant: AWQ-INT4Context: 2,048VRAM: 25.0 GBHeadroom: 10.2 GB
  • • Partial CPU offload: ~36% of layers run on CPU
6
tok/s
Estimated
Weights
19.00 GB
KV cache
4.00 GB
Activations
0.95 GB
Runtime
1.00 GB
Magistral 32B
32B
mistral
Quant: AWQ-INT4Context: 2,048VRAM: 25.0 GBHeadroom: 10.2 GB
  • • Partial CPU offload: ~36% of layers run on CPU
6
tok/s
Estimated
Weights
19.00 GB
KV cache
4.00 GB
Activations
0.95 GB
Runtime
1.00 GB
Qwen 3 Coder 32B
32B
qwen
Commercial OK
Quant: AWQ-INT4Context: 2,048VRAM: 25.0 GBHeadroom: 10.2 GB
  • • Partial CPU offload: ~36% of layers run on CPU
6
tok/s
Estimated
Weights
19.00 GB
KV cache
4.00 GB
Activations
0.95 GB
Runtime
1.00 GB

What if you upgraded?

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

+32 GB system RAM

Check the current price

Adds 32 GB to your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 49 new comfortable, 69 new tradeoff

  • • Qwen 3 0.6B
  • • Qwen 3 1.7B
  • • Llama 3.2 3B Instruct
  • • Gemma 3 270M

Add a second Intel Arc A770 16GB

Launch MSRP $349 (2022). Check the current price.

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: 94 new comfortable

  • • Qwen 3 0.6B
  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen 3 32B

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.

—
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.

—
DeepSeek V4 Flash (284B MoE)
284B
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

Measured here
Measured here - RunLocalAI ran this exact combo on owner hardware with public evidence.

Source-backed
Source-backed / community - a reproduced public source supports the speed, but it is not labeled as owner-measured.

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

Estimated
Estimated - formula based on VRAM bandwidth and model architecture; not a benchmark row.

RunLocalAI Will-It-Run Framework →

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