d1-omni-600M on local hardware
Estimated comfort for repository coding with Aider on a MacBook Pro M4 Pro 48GB.
d1-omni-600M
LiquidAI · other · 14,419 downloads
Vision
- Parameters
- 0.6B exact
- Context window
- 125K tokens
- Attention
- Standard (full attention)
- Layers · KV heads · head dim
- 16 · 8 · 64
- KV cache
- 12 KB/token · 0.4 GB at 32K
- Tool calling
- basic (inferred — no supporting signal)
- Thinking
- basic (inferred — no supporting signal)
- Vision
- good (from config)
- Commercial use
- check cardCheck the model card
- Import confidence
- medium · capabilities estimated
Weights by quantization
Q3_K_M
0.2 GB
gguf file size
Q4_K_M
0.2 GB
gguf file size
Q5_K_M
0.3 GB
gguf file size
Q6_K
0.3 GB
gguf file size
Q8_0
0.4 GB
gguf file size
F16 / BF16
0.7 GB
gguf file size
- • No chat template found; tool calling is inferred as limited (low confidence).
- • toolCalling: basic, inferred from missing signals (low confidence).
- • thinking: basic, inferred from missing signals (low confidence).
- • vision: good, inferred from config (low confidence).
- • Capability ratings are estimated from model size and name — this model hasn't been assessed by hand.
- • Commercial use unknown: Check the model card.
- • GGUF sizes come from community conversions matched by model name; equivalence and runtime support are not verified. MLX conversion availability is unverified.
d1-omni-600M — 6-bit
Technically Runs for your workload
Speed
250–330 tok/s
Excellent
Memory left
35 GB
of 48 GB
First word in
≈3 s
Excellent
All the details
- Your setup
- MacBook Pro M4 Pro 48 GB
- Workload
- Repository coding with Aider
- Runtime → tool
- LM Studio → Aider
- Memory used
- 1.8 GB
- Context
- 32K · up to 64K practical
- Tool support
- Official
- Use-case fit
- Poorly suited
Why?
- Model fits with approximately 35 GB of memory headroom.
- LM Studio supports hardware acceleration on this machine (Metal (Apple GPU)).
- Aider can connect to LM Studio (officially supported).
- Generation (250–330 tok/s) should be appropriate for interactive coding.
- Ingesting a prompt of 14K tokens takes ≈3 s; prompt processing keeps up with interactive coding.
- 32K working context is reasonable.
- Weak coding capability for interactive coding.
Why “Technically Runs” rather than “Borderline”?
- Workload suitability: Weak coding capability for interactive coding.
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.
- Hybrid/sliding attention performance varies more between runtimes.
Medium confidence