Llama-3-Blama-8B on local hardware
Estimated comfort for repository coding with Aider on a MacBook Pro M4 Pro 48GB.
Llama-3-Blama-8BOpen weights (restricted)
allenai · llama3 · 241 downloads
- Parameters
- 8.3B exact
- Context window
- 8K tokens
- Attention
- Standard (full attention)
- Layers · KV heads · head dim
- 32 · 8 · 128
- KV cache
- 128 KB/token · 4.0 GB at 32K
- Tool calling
- basic (inferred — no supporting signal)
- Thinking
- basic (inferred — no supporting signal)
- Vision
- basic (inferred — no supporting signal)
- Commercial use
- conditionalCommunity license and acceptable-use restrictions apply; large services need separate permission
- Import confidence
- medium · capabilities estimated
Weights by quantization
Q3_K_M
3.9 GB
computed · low confidence
Q4_K_M
4.8 GB
computed · low confidence
Q5_K_M
5.6 GB
computed · low confidence
Q6_K
6.5 GB
computed · low confidence
Q8_0
8.4 GB
computed · low confidence
F16 / BF16
16 GB
computed · low confidence
- • Assumes GGUF / MLX conversions of this model exist (they do for most popular models). Sizes are computed from bits per weight.
- • 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: basic, inferred from missing signals (low confidence).
- • Capability ratings are estimated from model size and name — this model hasn't been assessed by hand.
- • Commercial use conditional: Community license and acceptable-use restrictions apply; large services need separate permission.
Llama-3-Blama-8B — 6-bit
Acceptable for your workload
Speed
20–30 tok/s
Comfortable
Memory left
28 GB
of 48 GB
First word in
≈20 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
- 8.4 GB
- Context
- 8K · up to 8K practical
- Tool support
- Official
- Use-case fit
- Poorly suited
Why?
- Model fits with approximately 28 GB of memory headroom.
- LM Studio supports hardware acceleration on this machine (Metal (Apple GPU)).
- Aider can connect to LM Studio (officially supported).
- Generation (20–30 tok/s) should be appropriate for interactive coding.
- Ingesting a prompt of 7K tokens takes ≈20 s; prompt processing keeps up with interactive coding.
- 8K window; generation drops to 20–30 tok/s when it is full. The model is limited to 8K.
- Llama-3-Blama-8B supports at most 8K context; 32K was requested.
- Weak coding capability for interactive coding.
Why “Acceptable” rather than “Comfortable”?
- Workload suitability: Weak coding capability for interactive coding.
- Context: 8K window; generation drops to 20–30 tok/s when it is full. The model is limited to 8K.
- Generation: Expected 20–30 tok/s at ~7K tokens of context. Coding with repository context is comfortable from about 28 tok/s.
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.
Medium confidence