What local AI models can the Intel Arc A580 run?
37 of our 115 models, up to NVIDIA Nemotron 3.5 Bolt E4B. That is the largest current model that fits the Arc A580's 8 GB at Q4 with room for about 46K tokens of context (its full 64K with 8-bit KV cache), at about 30 tok/s estimate.
Memory type: GDDR6 (source) · Released: 2023 (source)
- Alchemist: speed uses an Intel Alchemist class fitted to one A770 Vulkan scoreboard point (52.56 tok/s, Llama 2 7B Q4_0); unverified beyond that.
- bus_bits: Intel's page lists none.
Specs from first-party pages (Intel), accessed 2026-10-18. Speeds use the Intel Arc A-series (Vulkan) constants (how).
As an Amazon Associate I earn from qualifying purchases.
Every model, largest that fits first
| Model | Quant | File | Fits? | Speed estimate | Max context estimate |
|---|---|---|---|---|---|
| NVIDIA Nemotron 3.5 Bolt E4B | Q4_K_M | 6.18 GB | Fits | ~30 tok/s | 46K · 64K (8-bit) |
| Qwen3.5-9B | Q4_K_M | 6.17 GB | Fits | ~28 tok/s | 24K · 46K (8-bit) |
| Ternary Bonsai 2 27B | PTQ1_0 ternary | 5.95 GB | Fits | ~29 tok/s | 15K · 29K (8-bit) |
| Microsoft Fara1.5 9B | Q4_K_M | 5.91 GB | Fits | ~29 tok/s | 32K · 61K (8-bit) |
| Xiaomi MiMo-V2.6-Distill-Qwen-9B | Q4_K_M | 5.84 GB | Fits | ~29 tok/s | 34K · 65K (8-bit) |
| ZoomGain-9B | Q4_K_M | 5.63 GB | Fits | ~30 tok/s | 40K · 76K (8-bit) |
| K2-Horizon-7B | Q4_K_M | 5.59 GB | Fits | ~33 tok/s | 9K · 17K (8-bit) |
| webAI TwIL-8B Math and code reasoning | Q4_K_M | 5.35 GB | Fits | ~34 tok/s | 9K · 18K (8-bit) |
| IBM Granite 4.2 8B | Q4_K_M | 5.35 GB | Fits | ~34 tok/s | 9K · 18K (8-bit) |
| PLaMo 3 Translate 8B Translation only | Q4_K_M | 5.28 GB | Fits | ~35 tok/s | 32K (full) |
| LFM2.5-8B-A1B | Q4_K_M | 5.16 GB | Fits | ~102 tok/s | 128K (full) |
| Gemma 4 E4B | Q4_K_M | 4.98 GB | Fits | ~37 tok/s | 117K · 128K (8-bit) |
| Spark-X2.6-4B | Q4_K_M | 3.54 GB | Fits | ~52 tok/s | 88K · 169K (8-bit) |
| Gemma 4 E2B | Q4_K_M | 3.46 GB | Fits | ~53 tok/s | 128K (full) |
| Qwen3.5-4B | Q4_K_M | 3.01 GB | Fits | ~53 tok/s | 118K · 223K (8-bit) |
| NVIDIA Nemotron 3 Nano 4B | Q4_K_M | 2.9 GB | Fits | ~55 tok/s | 244K · 256K (8-bit) |
| Microsoft Fara1.5 4B | Q4_K_M | 2.88 GB | Fits | ~55 tok/s | 122K · 231K (8-bit) |
| ZoomGain-4B | Q4_K_M | 2.71 GB | Fits | ~58 tok/s | 127K · 240K (8-bit) |
| IBM Granite 4.2 3B | Q4_K_M | 2.24 GB | Fits | ~82 tok/s | 56K · 106K (8-bit) |
| Raon-1 nano Early support | Q4_K_M | 2.08 GB | Weights fit context unknown | ~73 tok/s | Unknown (no KV data) |
| Ternary Bonsai 2 9B | PTQ1_0 ternary | 2 GB | Fits | ~75 tok/s | 149K · 256K (8-bit) |
| PLaMo 3 Translate 2B Translation only | Q4_K_M | 1.81 GB | Fits | ~102 tok/s | 32K (full) |
| LFM3-1.7B | Q4_K_M | 1.1 GB | Fits | ~120 tok/s | 256K (full) |
| LFM3-VL-2B | Q4_K_M | 1.1 GB | Fits | ~120 tok/s | 128K (full) |
| Ternary Bonsai 2 4B | PTQ1_0 ternary | 0.95 GB | Fits | ~132 tok/s | 180K · 256K (8-bit) |
| MiniCPM-V 4.7 1B | Q4_K_M | 0.67 GB | Fits | ~166 tok/s | 256K (full) |
| PLaMo 3 Translate 0.8B Translation only | Q4_K_M | 0.57 GB | Fits | ~323 tok/s | 32K (full) |
| BotPsy-0.8B | Q4_K_M | 0.53 GB | Fits | ~190 tok/s | 256K (full) |
| Ternary Bonsai 2 2B | PTQ1_0 ternary | 0.43 GB | Fits | ~211 tok/s | 256K (full) |
| Qwen3-8B Older | Q4_K_M | 5.03 GB | Fits | ~37 tok/s | 13K · 24K (8-bit) |
| Llama-3.1-8B-Instruct Older | Q4_K_M | 4.92 GB | Fits | ~37 tok/s | 15K · 29K (8-bit) |
| Qwen2.5-Coder-7B-Instruct Older | Q4_K_M | 4.68 GB | Fits | ~39 tok/s | 32K (full) |
| Mistral-7B-Instruct-v0.3 Older | Q4_K_M | 4.37 GB | Fits | ~42 tok/s | 19K · 32K (8-bit) |
| Qwen3-4B Older | Q4_K_M | 2.5 GB | Fits | ~74 tok/s | 29K · 40K (8-bit) |
| gemma-3-4b-it Older | Q4_K_M | 2.49 GB | Fits | ~74 tok/s | 128K (full) |
| Llama-3.2-3B-Instruct Older | Q4_K_M | 2.02 GB | Fits | ~91 tok/s | 42K · 79K (8-bit) |
| Qwen3-0.6B Older | Q4_K_M | 0.48 GB | Fits | ~384 tok/s | 40K (full) |
| NVIDIA-Nemotron-Nano-9B-v2 Older | Q4_K_M | 6.53 GB | No | — | — |
| Gemma 4 12B | Q4_K_M | 7.12 GB | No | — | — |
| gemma-3-12b-it Older | Q4_K_M | 7.3 GB | No | — | — |
| Mistral-Nemo-Instruct-2407 Older | Q4_K_M | 7.48 GB | No | — | — |
| JetBrains Mellum2.1 12B-A2.5B Thinking | Q4_K_M | 8.07 GB | No | — | — |
| Qwen3-14B Older | Q4_K_M | 9 GB | No | — | — |
| Qwen2.5-Coder-14B-Instruct Older | Q4_K_M | 8.99 GB | No | — | — |
| DeepSeek-R1-Distill-Qwen-14B Older | Q4_K_M | 8.99 GB | No | — | — |
| phi-4 | Q4_K_M | 9.05 GB | No | — | — |
| gpt-oss-20b | Q4_K_M | 11.67 GB | No | — | — |
| Mistral-Small-3.2-24B-Instruct-2506 | Q4_K_M | 14.33 GB | No | — | — |
| Devstral-Small-2505 | Q4_K_M | 14.33 GB | No | — | — |
| LFM2-24B-A2B Older | Q4_K_M | 14.42 GB | No | — | — |
| LFM2.5-24B-A2B | Q4_K_M | 14.53 GB | No | — | — |
| gemma-3-27b-it Older | Q4_K_M | 16.55 GB | No | — | — |
| Kvark Sparkle 1.1 27B | Q4_K_M | 16.81 GB | No | — | — |
| Gemma 4 26B A4B | Q4_K_M | 17.04 GB | No | — | — |
| Qwen3.8-27B | Q4_K_M | 17.44 GB | No | — | — |
| Microsoft Fara1.5 27B | Q4_K_M | 17.53 GB | No | — | — |
| IBM Granite 4.2 30B | Q4_K_M | 17.72 GB | No | — | — |
| Qwen3.6-27B | Q4_K_M | 17.98 GB | No | — | — |
| Qwen3.5-27B | Q4_K_M | 17.98 GB | No | — | — |
| Meta Muse Glimmer 30B | Q4_K_M | 18.39 GB | No | — | — |
| GLM-4.7-Flash | Q4_K_M | 18.31 GB | No | — | — |
| Qwen3-Coder-30B-A3B-Instruct Older | Q4_K_M | 18.56 GB | No | — | — |
| Gemma 4 31B | Q4_K_M | 18.32 GB | No | — | — |
| Qwen3-30B-A3B Older | Q4_K_M | 18.63 GB | No | — | — |
| PLaMo 3 Translate 31B Translation only | Q4_K_M | 19.53 GB | No | — | — |
| Raon-1 mini preview Early support | Q4_K_M | 19.69 GB | No | — | — |
| Qwen3-32B Older | Q4_K_M | 19.76 GB | No | — | — |
| Qwen2.5-Coder-32B-Instruct Older | Q4_K_M | 19.85 GB | No | — | — |
| DeepSeek-R1-Distill-Qwen-32B Older | Q4_K_M | 19.85 GB | No | — | — |
| Xing4.0-29B-A4B | Q4_K_M | 20.06 GB | No | — | — |
| Nanbeige4.3-33B | Q4_K_M | 20.79 GB | No | — | — |
| MiniCPM-V 4.7 35B-A3B | Q4_K_M | 21.17 GB | No | — | — |
| K2-Horizon-32B | Q4_K_M | 21.08 GB | No | — | — |
| NVIDIA Nemotron 3.5 Bolt 74B-A9B 24GB (2-bit) | native 2-bit | 22.02 GB | No | — | — |
| Qwen3.6-35B-A3B | Q4_K_M | 22.29 GB | No | — | — |
| Qwen3.5-35B-A3B | Q4_K_M | 22.29 GB | No | — | — |
| K2-Horizon-MoVA-36B-A4B | Q4_K_M | 22.37 GB | No | — | — |
| NVIDIA Nemotron 3.5 Lightning 30B-A3B | Q4_K_M | 25.48 GB | No | — | — |
| Recursive Flint 40B-A2.5B | Q4_1 | 25.99 GB | No | — | — |
| Ripple-65B Preview | Q4_K_M | 38.8 GB | No | — | — |
| Llama-3.3-70B-Instruct Older | Q4_K_M | 42.52 GB | No | — | — |
| DeepSeek-R1-Distill-Llama-70B Older | Q4_K_M | 42.52 GB | No | — | — |
| Qwen2.5-72B-Instruct Older | Q4_K_M | 47.42 GB | No | — | — |
| Qwen3-Coder-Next | Q4_K_M | 48.53 GB | No | — | — |
| Aleph Alpha Kolibri-1 78B-A3.5B | Q4_K_M | 49.76 GB | No | — | — |
| NVIDIA Nemotron 3.5 Bolt 74B-A9B | UD-Q4_K_XL | 50.22 GB | No | — | — |
| gpt-oss-120b | Q4_K_M | 62.84 GB | No | — | — |
| NVIDIA Nemotron 3.5 Super VL 120B-A12B | Q4_K_M | 70.1 GB | No | — | — |
| Mistral Small 4 119B | Q4_K_M | 72.64 GB | No | — | — |
| GLM-4.5-Air Older | Q4_K_M | 73.5 GB | No | — | — |
| Qwen3.5-122B-A10B | Q4_K_M | 77.62 GB | No | — | — |
| Mistral Medium 3.5 128B | Q4_K_M | 78.41 GB | No | — | — |
| Ornith-1.5-122B | Q4_K_M | 78.92 GB | No | — | — |
| NVIDIA Nemotron 3 Super 120B-A12B Older | UD-Q4_K_M | 82.54 GB | No | — | — |
| Swift 1.5 Qwen3.8-Flash-Next | Q4_K_M | 119.6 GB | No | — | — |
| Qwen3.8-Flash-Next | Q4_K_M | 119.6 GB | No | — | — |
| StepFun Step 3.7 Flash | UD-Q4_K_M | 122.09 GB | No | — | — |
| Qwen3-235B-A22B | Q4_K_M | 142.15 GB | No | — | — |
| MiniMax-M3.1-Flash Unsloth 2-bit | UD-Q2_K_XL | 143.91 GB | No | — | — |
| DeepSeek-V4-Flash | UD-Q4_K_XL | 155.1 GB | No | — | — |
| MiniMax-M3.1-Flash Q2_K | Q2_K | 155.91 GB | No | — | — |
| Thinking Machines Inkling-Small Older | Q4_K_M | 159.34 GB | No | — | — |
| Xiaomi MiMo-V2.6-Flash 309B-A15B | MXFP4 | 167.37 GB | No | — | — |
| GLM-5.3-Flash | UD-Q4_K_XL | 199.71 GB | No | — | — |
| MiniMax-M3.1-Flash | Q4_K_M | 258.01 GB | No | — | — |
| Reflection Beam 1.0 501B-A23B | Q4_K_M | 302.41 GB | No | — | — |
| Thinking Machines Inkling 2 Small Early support | UD-Q4_K_XL | 354.15 GB | No | — | — |
| inclusionAI Ling-3.1-flash 560B-A25B | Q4_K_M | 357.97 GB | No | — | — |
| DeepSeek-V4.1-Flash (1017) | UD-Q4_K_XL | 500.71 GB | No | — | — |
| Meta Muse Spark Open 816B-A42B | UD-Q4_K_XL | 505.5 GB | No | — | — |
| Mistral Large 4 | UD-Q4_K_XL | 605 GB | No | — | — |
Q4_K_M unless the row says otherwise; UD- sizes are unsloth dynamic quants, the only Q4 build published for those models. Max context is an estimate of the longest context whose KV cache fits beside the model: default FP16 cache, then 8-bit (q8_0).
Speed calculator
estimateEstimate = bandwidth ÷ GB read per token (the model's listed GGUF file: Q4_K_M for most models, otherwise the quant named in the list; scaled by active/total parameters for MoE), scaled by a per-platform efficiency and fixed per-token costs calibrated to 45 measured llama.cpp benchmarks (2025–26). Fit = file size + 1.5 GB headroom ≤ total VRAM (on Macs, the part of unified memory macOS lets the GPU use by default), and room for at least 4K tokens of context with an 8-bit KV cache. For a model with no KV cache data, only the file and headroom are checked, so a fit says nothing about context. Multi-GPU: VRAM adds, speed stays one card's (a layer split runs the cards in turn); max context uses the total. Speed is for short context. Max context = what is left after the file and a 1 GB runtime reserve ÷ KV cache bytes per token, default FP16 and 8-bit (q8_0) cache. How speed works · how context works