Qwen 3.5 9B runs at 81 tok/s on a 96 GB M3 Ultra, a community run reported by github.com (llama.cpp, Q4_K_M, 75-token chat prompt, three greedy 256-token continuations). It needs about 7 GB of unified memory. It is Alibaba's 9B dense model, released under the Apache 2.0 licence.
Want to run Qwen 3.5 9B faster — or step up to bigger models? Find your Mac →This is a community run: a real run, reported by its source and linked below. The index records it as given and never adjusts it.
| Metric | Value |
|---|---|
| Tokens per second | community81 tok/s |
| Provenance | community run · github.com |
| Quantization | Q4_K_M |
| Engine | llama.cpp |
| Context | 75-token chat prompt, three greedy 256-token continuations |
| Figure dated | 2026-11-07 |
| Minimum RAM | 7 GB |
| Parameters | 9B |
| Chip bandwidth | 819 GB/s |
Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (7 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.
| Speed | Quant | Engine | Mac RAM | Context | Source | Note |
|---|---|---|---|---|---|---|
| community114.1 tok/s | 4-bit | MLX | 96 GB | 75-token chat prompt, three greedy 256-token continuations | github.com | M3 Ultra, 60-core GPU (819 GB/s, the same as the 80-core part), 96 GB, macOS 26.4.1. mlx-lm on MLX (versions in the repo's M3 evidence folder), Kapitsa's MLX 4-bit weights. Run by the Kapitsa engine's developers with their own harness. |
| community81 tok/s | Q4_K_M | llama.cpp | 96 GB | 75-token chat prompt, three greedy 256-token continuations | github.com | M3 Ultra, 60-core GPU (819 GB/s, the same as the 80-core part), 96 GB, macOS 26.4.1. llama.cpp (build in the repo's M3 evidence folder), unsloth Q4_K_M. Run by the Kapitsa engine's developers with their own harness. |
Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-11-14:
MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:
Downloads: Ollama page → · Hugging Face model card →
The 81 tok/s figure above came from llama.cpp at Q4_K_M; other runtimes and quants run at different speeds.
Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.
| Chip | Speed | Quant | Engine | Bandwidth |
|---|---|---|---|---|
| M5 Ultra | community167 tok/s | 4-bit | MLX | 1228 GB/s |
| M5 Max | estimated81 tok/s | Q4_K_M | Ollama | 614 GB/s |
| M4 Pro | community39 tok/s | Q4_K_M | llama.cpp | 273 GB/s |
| M6 | estimated30 tok/s | Q4_K_M | MLX | 170 GB/s |
| M4 | estimated18 tok/s | Q4_K_M | LM Studio | 120 GB/s |
| M3 | estimated15 tok/s | Q4_K_M | Ollama | 100 GB/s |
| M1 | estimated10 tok/s | Q4_K_M | Ollama | 68 GB/s |
Alibaba's 9B model, ~81 tok/s on M5 Max. Apache 2.0 license, LLMCheck capability 18/50.
Apache 2.0 licence · 9B · 262K context · LLMCheck capability 18/50 · see its leaderboard rank →
Estimated, not measured: the index’s minimum for Qwen 3.5 9B (7 GB — the weights at the quant that fits, plus ~2 GB) plus the KV cache for that many tokens, computed from its config.json. hybrid: full attention on 8 of 32 layers; Gated DeltaNet layers keep a constant state. A 16-bit KV cache is the default in llama.cpp, Ollama, LM Studio and mlx-lm; a q8 cache halves the KV part. Coding agents hold 64K tokens or more. Runtimes also add a buffer that grows with context, so leave a few GB spare. macOS lets the GPU use only part of a Mac’s memory by default (figures for an M3 Ultra Mac on macOS 15, the lower default; macOS 26 allows more): “fits” means within the GPU memory a Mac of that tier can use with the limit raised, a tier tagged raise GPU limit fits only after sudo sysctl iogpu.wired_limit_mb raises it (the tooltip has the exact command), and the last column is the smallest Mac memory size whose default limit holds it (the GPU memory limit).
Qwen 3.5 9B needs about 7 GB of unified memory. These Apple Silicon Macs have enough to run it.
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.
See how Qwen 3.5 9B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard