Apple M1 Ultra
128 GB decides what fits. 800 GB/s decides how fast it runs once it does.
Computed for 128 GB, the largest configuration. The Apple M1 Ultra is also sold with 64 GB, and what fits changes with it.
Open in the calculator →Best models for 128 GB, on every card that size →
Find one: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
- Largest popular model that fitsQwen3.8-Flash-Next180B params · Q4_K_M · needs 111.6 GB~95 tok/s Faster than you readOpen in the calculator →
- Best fast pickStep-3.5-Flash199B params · Q4_K_M · needs 127.0 GB~47 tok/s Faster than you readOpen in the calculator →
- Most downloaded that fitsQwen3.8-27B28B params · Q4_K_M · needs 18.6 GB~39 tok/s Faster than you readOpen in the calculator →
At 8,192 tokens of context with the whole model in device memory. Speeds are estimates from memory bandwidth, not benchmarks run on this card.
248 of 320 fit entirely
248 of the 320 models the engine can size fit entirely in device memory at Q4_K_M where it is published, otherwise the nearest published format, and 8,192 tokens. Unified memory is one pool, so there is no second memory tier to spill into; the remaining 72 do not run at this context.
Featured models · Q4_K_M at 8,192 tokens, including offload
| Model | Needs | Verdict | Decode | Calculator |
|---|---|---|---|---|
| Qwen3.5-2B2.3B parameters | 2.32 GB | fits | ~136 tok/s | Open → |
| NVIDIA-Nemotron-3-Nano-4B-BF164.0B parameters | 3.46 GB | fits | ~108 tok/s | Open → |
| Qwen3-VL-8B-Instruct8.8B parameters | 7.04 GB | fits | ~74 tok/s | Open → |
| Qwen3.5-9B9.7B parameters | 7.05 GB | fits | ~82 tok/s | Open → |
| gemma-4-12B-it12B parameters | 9.54 GB | fits | ~60 tok/s | Open → |
| gpt-oss-20b21B parameters | 13.8 GB | fits | ~111 tok/s | Open → |
| Qwen3.8-27B28B parameters | 18.6 GB | fits | ~39 tok/s | Open → |
| Qwen3.6-27B28B parameters | 18.6 GB | fits | ~39 tok/s | Open → |
| Kimi-Linear-48B-A3B-Instruct49B parameters | 30.4 GB | fits | ~122 tok/s | Open → |
| Qwen3.8-Flash-Next180B parameters | 111.6 GB | fits | ~95 tok/s | Open → |
| DeepSeek-V4-Flash-Vision-Exp305B parameters | 188.1 GB | short by 60.1 GB | does not run | Open → |
| GLM-5.3-Flash321B parameters | 198.3 GB | short by 70.3 GB | does not run | Open → |
These examples are selected from prominent labs using the catalogue’s latest Hugging Face 30-day downloads and repository-creation freshness signal, with newer releases guaranteed a place. Offloaded rows assume 32 GB of system RAM, and a speed is only shown for a row that runs. Fitting in memory is not the same as loading: whether the runtime and version you have supports each architecture and format on this machine has not been tested here. Each “Open” link carries the same model, format, context and RAM into the calculator.
Fits entirely in Apple M1 Ultra (128 GB) memory — 248 of 320 sized models
The most demanding model that fits is Step-3.5-Flash at Q4_K_M: 127.0 GB of the 128 GB, leaving 1.03 GB spare.
Fully resident at 8,192 tokens (or the model’s own maximum, where that is shorter), offload off, at 800 GB/s. Each row is a run of the engine for this configuration; the rows start with current, prominent releases and “fits” is memory, not a tested runtime. Older or less prominent models remain available through this search and “Show all”.
Showing 40 of 248 models that fit.
| Model | Format | Needs | Spare | Decode | Downloads / 30d | Calculator |
|---|---|---|---|---|---|---|
| Qwen3.8-27BQwen · 28B params | Q4_K_M | 18.6 GB | 109.4 GB | ~39 tok/s | 6.9M | Open → |
| Qwen3.8-Flash-NextNEWQwen · 180B params | Q4_K_M | 111.6 GB | 16.4 GB | ~95 tok/s | 1.4M | Open → |
| gemma-4-26B-A4B-itGoogle · 26B params | Q4_K_M | 16.8 GB | 111.2 GB | ~108 tok/s | 13M | Open → |
| gemma-4-31B-itGoogle · 31B params | Q4_K_M | 22.2 GB | 105.8 GB | ~30 tok/s | 9.9M | Open → |
| Qwen3.5-9BQwen · 9.7B params | Q4_K_M | 7.05 GB | 121.0 GB | ~82 tok/s | 9M | Open → |
| Qwen3.5-4BQwen · 4.7B params | Q4_K_M | 3.98 GB | 124.0 GB | ~108 tok/s | 7.8M | Open → |
| Qwen3.6-35B-A3BQwen · 36B params | Q4_K_M | 23.1 GB | 104.9 GB | ~123 tok/s | 3.3M | Open → |
| gemma-4-12B-itGoogle · 12B params | Q4_K_M | 9.54 GB | 118.5 GB | ~60 tok/s | 1.9M | Open → |
| Qwen3.6-27BQwen · 28B params | Q4_K_M | 18.6 GB | 109.4 GB | ~39 tok/s | 2.5M | Open → |
| Qwen3.5-2BQwen · 2.3B params | Q4_K_M | 2.32 GB | 125.7 GB | ~136 tok/s | 4.9M | Open → |
| gemma-4-E4B-itGoogle · 8.0B params | Q4_K_M | 5.86 GB | 122.1 GB | ~103 tok/s | 4.4M | Open → |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA · 32B params | Q4_K_M | 20.3 GB | 107.7 GB | ~32 tok/s | 530K | Open → |
| NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA · 4.0B params | Q4_K_M | 3.46 GB | 124.5 GB | ~108 tok/s | 3.4M | Open → |
| gemma-4-E2B-itGoogle · 5.1B params | Q4_K_M | 4.02 GB | 124.0 GB | ~139 tok/s | 3M | Open → |
| Qwen3.5-0.8BQwen · 873M params | Q4_K_M | 1.46 GB | 126.5 GB | ~155 tok/s | 2.6M | Open → |
| Qwen3-VL-8B-InstructQwen · 8.8B params | Q4_K_M | 7.04 GB | 121.0 GB | ~74 tok/s | 14.6M | Open → |
| Qwen3.5-27BQwen · 28B params | Q4_K_M | 18.6 GB | 109.4 GB | ~39 tok/s | 1.9M | Open → |
| North-Micro-Vision-InstructCohereLabs · 2.5B params | Q4_K_M | 2.99 GB | 125.0 GB | ~122 tok/s | 180.7K | Open → |
| Qwen3.5-35B-A3BQwen · 36B params | Q4_K_M | 23.1 GB | 104.9 GB | ~123 tok/s | 1.6M | Open → |
| NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA · 124B params | Q4_K_M | 76.9 GB | 51.1 GB | ~9.3 tok/sSlow | 1.2M | Open → |
| granite-4.2-8bIBM · 8.8B params | Q4_K_M | 7.49 GB | 120.5 GB | ~70 tok/s | 128.4K | Open → |
| GLM-4.7-Flashzai-org · 31B params | Q4_K_M | 20.4 GB | 107.6 GB | ~31 tok/s | 1.8M | Open → |
| granite-4.1-3bIBM · 3.4B params | Q4_K_M | 3.72 GB | 124.3 GB | ~107 tok/s | 521.8K | Open → |
| LFM2.5-2.6BLiquidAI · 2.7B params | Q4_K_M | 2.61 GB | 125.4 GB | ~125 tok/s | 108.1K | Open → |
| Qwen3-VL-4B-InstructQwen · 4.4B params | Q4_K_M | 4.72 GB | 123.3 GB | ~94 tok/s | 3.5M | Open → |
| granite-4.1-30bIBM · 29B params | Q4_K_M | 20.4 GB | 107.6 GB | ~31 tok/s | 301.5K | Open → |
| Qwen3.5-122B-A10BQwen · 125B params | Q4_K_M | 77.9 GB | 50.1 GB | ~80 tok/s | 512.6K | Open → |
| Qwen3-VL-2B-InstructQwen · 2.1B params | Q4_K_M | 3.05 GB | 125.0 GB | ~119 tok/s | 2.8M | Open → |
| granite-4.2-3bIBM · 3.7B params | Q4_K_M | 3.72 GB | 124.3 GB | ~107 tok/s | 50.6K | Open → |
| LFM2.5-230MLiquidAI · 230M params | Q4_K_M | 1.05 GB | 126.9 GB | ~166 tok/s | 88.6K | Open → |
| Qwen3-0.6BQwen · 752M params | Q4_K_M | 2.22 GB | 125.8 GB | ~134 tok/s | 29.7M | Open → |
| Qwen3-Coder-NextQwen · 80B params | Q4_K_M | 50.0 GB | 78.0 GB | ~106 tok/s | 596.3K | Open → |
| gpt-oss-20bOpenAI · 21B params | Q4_K_M | 13.8 GB | 114.2 GB | ~111 tok/s | 6.6M | Open → |
| granite-4.2-30bIBM · 29B params | Q4_K_M | 20.7 GB | 107.3 GB | ~31 tok/s | 35.8K | Open → |
| granite-4.1-8bIBM · 8.8B params | Q4_K_M | 7.49 GB | 120.5 GB | ~70 tok/s | 179.3K | Open → |
| NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA · 32B params | Q4_K_M | 20.3 GB | 107.7 GB | ~32 tok/s | 875.2K | Open → |
| gpt-oss-120bOpenAI · 117B params | Q4_K_M | 71.9 GB | 56.1 GB | ~96 tok/s | 4.5M | Open → |
| LFM2.5-VL-3BLiquidAI · 3.1B params | Q4_K_M | 2.85 GB | 125.1 GB | ~125 tok/s | 26.7K | Open → |
| MiMo-V2.6-Distill-Qwen-9BNEWXiaomiMiMo · 9.4B params | Q4_K_M | 6.90 GB | 121.1 GB | ~82 tok/s | 14.6K | Open → |
| Qwen3-4B-Instruct-2507Qwen · 4.0B params | Q4_K_M | 4.72 GB | 123.3 GB | ~94 tok/s | 3.7M | Open → |
Sized at the format most people actually download, not at FP16. The catalogue ordered by downloads →
Find the Apple M1 Ultra: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
The Apple M1 Ultra, model by model
One page per model: whether it fits this device, at which formats, and how fast.
- Qwen3-0.6B
- Qwen3-VL-8B-Instruct
- gemma-4-26B-A4B-it
- Qwen3-8B
- gemma-4-31B-it
- Qwen3.5-9B
- Qwen2.5-0.5B-Instruct
- Qwen2.5-7B-Instruct
- Qwen3.5-4B
- Qwen3-4B
- Qwen2.5-1.5B-Instruct
- Qwen3.8-27B
All 70Fewer
- gpt-oss-20b
- Qwen2.5-VL-7B-Instruct
- GLM-5.3-Flash
- Qwen3.5-2B
- dolphin-2.9.1-yi-1.5-34b
- DeepSeek-V4-Flash-0731
- gpt-oss-120b
- gemma-4-E4B-it
- Qwen2.5-3B-Instruct
- Qwen3-32B
- Qwen3-4B-Instruct-2507
- DeepSeek-V3.2
- Qwen3-VL-4B-Instruct
- pythia-160m
- NVIDIA-Nemotron-3-Nano-4B-BF16
- Qwen3.6-35B-A3B
- Qwen3-1.7B
- gemma-4-E2B-it
- OTel-2.0-LLM-31B-IT
- Qwen3-VL-2B-Instruct
- Qwen3-14B
- Qwen3.5-0.8B
- JiRackUltra_1b
- Qwen3.6-27B
- Qwen2.5-VL-3B-Instruct
- Qwen2.5-Coder-7B-Instruct
- Mistral-7B-Instruct-v0.3
- Qwen2.5-32B-Instruct
- gemma-4-12B-it
- Qwen3.5-27B
- SmolLM2-135M-Instruct
- SmolLM2-135M
- GLM-4.7-Flash
- Mistral-7B-Instruct-v0.2
- Qwen2.5-Coder-14B-Instruct
- Qwen2.5-14B-Instruct
- Qwen3.5-35B-A3B
- Qwen3-30B-A3B
- Qwen2.5-0.5B
- Ornith-1.0-35B
- pythia-70m-deduped
- DeepSeek-V3-0324
- Qwen3.8-Flash-Next
- GLM-5.3
- TinyLlama-1.1B-Chat-v1.0
- DeepSeek-V3
- Kimi-K3
- NVIDIA-Nemotron-3-Super-120B-A12B-BF16
- MiniMax-M2.7
- DeepSeek-V4-Flash
- MiniCPM5-2B
- DeepSeek-R1
- DeepSeek-R1-Distill-Qwen-1.5B
- Ornith-1.0-9B
- DeepSeek-V4-Flash-Vision-Exp
- DeepSeek-Coder-V2-Lite-Instruct
- Qwen2.5-Coder-32B-Instruct
- NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
The specification behind every figure
What the manufacturer publishes for this device, and the pages it was read from.
Manufacturer specification
| Memory scope | unified-system |
|---|---|
| Capacity | 128 GB |
| Published options | 64 GB, 128 GB |
| Bandwidth | 800 GB/s |
| Memory type | unified memory |
| Bus width | Not published |
| FP32 peak | Not published |
| Dense matrix peak | Not published without sparsity |
| Power | Not published |
Source ledger
Caveats
- Capacity and bandwidth are the maxima Apple publishes for this chip; lower configurations exist and run slower. No VRAM capacity is claimed, and the operating system's own use is not subtracted.
- Apple publishes no peak throughput figure for this chip, so no compute roof is priced for it and time to first token is withheld.
Published capacity is a hardware ceiling, not guaranteed free runtime memory. The calculator shows the runtime reserve separately rather than folding it into a single number.
Run the diagnostic on the Apple M1 Ultra →