Xing4.0-29B-A4B on local hardware
Estimated comfort for repository coding with Aider on a MacBook Pro M4 Pro 48GB.
Xing4.0-29B-A4BOpen source
XingChen-AGI · apache-2.0 · 43,140 downloads
Mixture of expertsReasoning / thinking mode
- Parameters
- 31B exact
- Active per token
- ≈5.6B (4 of 64 experts)
- Context window
- 4K tokensRoPE-extended to 256K (quality degrades past native — treat long-context ratings as optimistic)
- Attention
- Multi-head latent attention (compressed KV)
- Layers · KV heads · head dim
- 40 · 32 · 112
- KV cache
- 45 KB/token · 1.4 GB at 32K
- Tool calling
- good (from chat template)
- Thinking
- good (from chat template)
- Vision
- basic (inferred — no supporting signal)
- Commercial use
- allowedRetain the required license and attribution notices
- Import confidence
- medium · capabilities estimated
Weights by quantization
Q3_K_M
13 GB
gguf file size
Q4_K_M
18 GB
gguf file size
Q5_K_M
21 GB
gguf file size
Q6_K
24 GB
gguf file size
Q8_0
31 GB
gguf file size
F16 / BF16
58 GB
gguf file size
- • Context native 4096, rope-extended to 262144 (yarn); quality degrades past native — treat long-context ratings as optimistic.
- • vision: basic, inferred from missing signals (low confidence).
- • Capability ratings are estimated from model size and name — this model hasn't been assessed by hand.
- • GGUF sizes come from community conversions matched by model name; equivalence and runtime support are not verified. MLX conversion availability is unverified.
Xing4.0-29B-A4B — 6-bit
Acceptable for your workload
Speed
25–35 tok/s
Comfortable
Memory left
12 GB
of 48 GB
First word in
≈8 s
Comfortable
All the details
- Your setup
- MacBook Pro M4 Pro 48 GB
- Workload
- Repository coding with Aider
- Runtime → tool
- LM Studio → Aider
- Memory used
- 25 GB
- Context
- 4K · up to 4K practical
- Tool support
- Official
- Use-case fit
- Partly suited
Why?
- Model fits with approximately 12 GB of memory headroom.
- LM Studio supports hardware acceleration on this machine (Metal (Apple GPU)).
- Aider can connect to LM Studio (officially supported).
- Generation (25–35 tok/s) should be appropriate for interactive coding.
- Ingesting a prompt of 3K tokens takes ≈8 s; prompt processing keeps up with interactive coding.
- 4K window; generation drops to 25–35 tok/s when it is full. The model is limited to 4K. Aider needs at least 8K for its system prompt and tool definitions.
- Weak coding capability for interactive coding.
- Xing4.0-29B-A4B supports at most 4K context; 32K was requested.
Why “Acceptable” rather than “Comfortable”?
- Workload suitability: Weak coding capability for interactive coding.
- Context: 4K window; generation drops to 25–35 tok/s when it is full. The model is limited to 4K. Aider needs at least 8K for its system prompt and tool definitions.
How sure are we?
Medium confidenceEstimated from bandwidth and compute, calibrated against 2 verified benchmarks of other models on this same chip (measured with a different engine, so calibration is partial).
- Calibrated with verified benchmarks of other models on this chip.
- MoE performance varies more between runtimes.
Medium confidence